update

.github/ISSUE_TEMPLATE/bug-report.yml

@@ -66,32 +66,32 @@ body:
         Questions on DiffusionPipeline (Saving, Loading, From pretrained, ...):
 
         Questions on pipelines:
-        - Stable Diffusion @yiyixuxu @DN6 @sayakpaul 
-        - Stable Diffusion XL @yiyixuxu @sayakpaul @DN6 
-        - Kandinsky @yiyixuxu 
-        - ControlNet @sayakpaul @yiyixuxu @DN6 
-        - T2I Adapter @sayakpaul @yiyixuxu @DN6 
-        - IF @DN6 
-        - Text-to-Video / Video-to-Video @DN6 @sayakpaul 
-        - Wuerstchen @DN6 
+        - Stable Diffusion @yiyixuxu @DN6 @sayakpaul @patrickvonplaten
+        - Stable Diffusion XL @yiyixuxu @sayakpaul @DN6 @patrickvonplaten
+        - Kandinsky @yiyixuxu @patrickvonplaten
+        - ControlNet @sayakpaul @yiyixuxu @DN6 @patrickvonplaten
+        - T2I Adapter @sayakpaul @yiyixuxu @DN6 @patrickvonplaten
+        - IF @DN6 @patrickvonplaten
+        - Text-to-Video / Video-to-Video @DN6 @sayakpaul @patrickvonplaten
+        - Wuerstchen @DN6 @patrickvonplaten
         - Other: @yiyixuxu @DN6
 
         Questions on models:
-        - UNet @DN6 @yiyixuxu @sayakpaul 
-        - VAE @sayakpaul @DN6 @yiyixuxu 
-        - Transformers/Attention @DN6 @yiyixuxu @sayakpaul @DN6 
+        - UNet @DN6 @yiyixuxu @sayakpaul @patrickvonplaten
+        - VAE @sayakpaul @DN6 @yiyixuxu @patrickvonplaten
+        - Transformers/Attention @DN6 @yiyixuxu @sayakpaul @DN6 @patrickvonplaten
 
-        Questions on Schedulers: @yiyixuxu 
+        Questions on Schedulers: @yiyixuxu @patrickvonplaten
 
-        Questions on LoRA: @sayakpaul 
+        Questions on LoRA: @sayakpaul @patrickvonplaten
 
-        Questions on Textual Inversion: @sayakpaul 
+        Questions on Textual Inversion: @sayakpaul @patrickvonplaten
 
         Questions on Training: 
-        - DreamBooth @sayakpaul 
-        - Text-to-Image Fine-tuning @sayakpaul 
-        - Textual Inversion @sayakpaul 
-        - ControlNet @sayakpaul 
+        - DreamBooth @sayakpaul @patrickvonplaten
+        - Text-to-Image Fine-tuning @sayakpaul @patrickvonplaten
+        - Textual Inversion @sayakpaul @patrickvonplaten
+        - ControlNet @sayakpaul @patrickvonplaten
 
         Questions on Tests: @DN6 @sayakpaul @yiyixuxu 
 
@@ -99,7 +99,7 @@ body:
 
         Questions on JAX- and MPS-related things: @pcuenca
 
-        Questions on audio pipelines: @DN6 
+        Questions on audio pipelines: @DN6 @patrickvonplaten
         
 
         

.github/PULL_REQUEST_TEMPLATE.md

@@ -38,13 +38,13 @@ members/contributors who may be interested in your PR.
 
 Core library:
 
-- Schedulers: @yiyixuxu 
-- Pipelines:  @sayakpaul @yiyixuxu @DN6
-- Training examples: @sayakpaul 
-- Docs: @stevhliu and @sayakpaul
+- Schedulers: @yiyixuxu and @patrickvonplaten
+- Pipelines:  @patrickvonplaten and @sayakpaul
+- Training examples: @sayakpaul and @patrickvonplaten
+- Docs: @stevhliu and @yiyixuxu
 - JAX and MPS: @pcuenca
 - Audio: @sanchit-gandhi
-- General functionalities: @sayakpaul @yiyixuxu @DN6
+- General functionalities: @patrickvonplaten and @sayakpaul
 
 Integrations:
 

.github/workflows/benchmark.yml

@@ -1,7 +1,6 @@
 name: Benchmarking tests
 
 on:
-  workflow_dispatch:
   schedule:
     - cron: "30 1 1,15 * *" # every 2 weeks on the 1st and the 15th of every month at 1:30 AM
 
@@ -31,9 +30,9 @@ jobs:
           nvidia-smi
       - name: Install dependencies
         run: |
-          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-          python -m uv pip install -e [quality,test]
-          python -m uv pip install pandas peft
+          apt-get update && apt-get install libsndfile1-dev libgl1 -y
+          python -m pip install -e .[quality,test]
+          python -m pip install pandas peft
       - name: Environment
         run: |
           python utils/print_env.py

.github/workflows/build_docker_images.yml

@@ -1,58 +1,21 @@
-name: Test, build, and push Docker images
+name: Build Docker images (nightly)
 
 on:
-  pull_request: # During PRs, we just check if the changes Dockerfiles can be successfully built
-    branches:
-      - main
-    paths:
-      - "docker/**"
   workflow_dispatch:
   schedule:
     - cron: "0 0 * * *" # every day at midnight
 
 concurrency:
-  group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}
-  cancel-in-progress: true
+  group: docker-image-builds
+  cancel-in-progress: false
 
 env:
   REGISTRY: diffusers
-  CI_SLACK_CHANNEL: ${{ secrets.CI_DOCKER_CHANNEL }}
 
 jobs:
-  test-build-docker-images:
-    runs-on: [ self-hosted, intel-cpu, 8-cpu, ci ]
-    if: github.event_name == 'pull_request'
-    steps:
-      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v1
-      
-      - name: Check out code
-        uses: actions/checkout@v3
-      
-      - name: Find Changed Dockerfiles
-        id: file_changes
-        uses: jitterbit/get-changed-files@v1
-        with:
-          format: 'space-delimited'
-          token: ${{ secrets.GITHUB_TOKEN }}
-      
-      - name: Build Changed Docker Images
-        run: |
-          CHANGED_FILES="${{ steps.file_changes.outputs.all }}"
-          for FILE in $CHANGED_FILES; do
-            if [[ "$FILE" == docker/*Dockerfile ]]; then
-              DOCKER_PATH="${FILE%/Dockerfile}"
-              DOCKER_TAG=$(basename "$DOCKER_PATH")
-              echo "Building Docker image for $DOCKER_TAG"
-              docker build -t "$DOCKER_TAG" "$DOCKER_PATH"
-            fi
-          done
-        if: steps.file_changes.outputs.all != ''
+  build-docker-images:
+    runs-on: ubuntu-latest
 
-  build-and-push-docker-images:
-    runs-on: [ self-hosted, intel-cpu, 8-cpu, ci ]
-    if: github.event_name != 'pull_request'
-    
     permissions:
       contents: read
       packages: write
@@ -73,13 +36,13 @@ jobs:
     steps:
       - name: Checkout repository
         uses: actions/checkout@v3
-      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v1
+
       - name: Login to Docker Hub
         uses: docker/login-action@v2
         with:
           username: ${{ env.REGISTRY }}
           password: ${{ secrets.DOCKERHUB_TOKEN }}
+
       - name: Build and push
         uses: docker/build-push-action@v3
         with:
@@ -87,27 +50,3 @@ jobs:
           context: ./docker/${{ matrix.image-name }}
           push: true
           tags: ${{ env.REGISTRY }}/${{ matrix.image-name }}:latest
-
-      - name: Post to a Slack channel
-        id: slack
-        uses: slackapi/slack-github-action@6c661ce58804a1a20f6dc5fbee7f0381b469e001
-        with:
-          # Slack channel id, channel name, or user id to post message.
-          # See also: https://api.slack.com/methods/chat.postMessage#channels
-          channel-id: ${{ env.CI_SLACK_CHANNEL }}
-          # For posting a rich message using Block Kit
-          payload: |
-            {
-              "text": "${{ matrix.image-name }} Docker Image build result: ${{ job.status }}\n${{ github.event.head_commit.url }}",
-              "blocks": [
-                {
-                  "type": "section",
-                  "text": {
-                    "type": "mrkdwn",
-                    "text": "${{ matrix.image-name }} Docker Image build result: ${{ job.status }}\n${{ github.event.head_commit.url }}"
-                  }
-                }
-              ]
-            }
-        env:
-          SLACK_BOT_TOKEN: ${{ secrets.SLACK_CIFEEDBACK_BOT_TOKEN }}

.github/workflows/build_documentation.yml

@@ -7,10 +7,6 @@ on:
       - doc-builder*
       - v*-release
       - v*-patch
-    paths:
-      - "src/diffusers/**.py"
-      - "examples/**"
-      - "docs/**"
 
 jobs:
   build:

.github/workflows/build_pr_documentation.yml

@@ -2,10 +2,6 @@ name: Build PR Documentation
 
 on:
   pull_request:
-    paths:
-      - "src/diffusers/**.py"
-      - "examples/**"
-      - "docs/**"
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}

.github/workflows/nightly_tests.yml

@@ -1,7 +1,6 @@
-name: Nightly and release tests on main/release branch
+name: Nightly tests on main
 
 on:
-  workflow_dispatch:
   schedule:
     - cron: "0 0 * * *" # every day at midnight
 
@@ -13,348 +12,106 @@ env:
   PYTEST_TIMEOUT: 600
   RUN_SLOW: yes
   RUN_NIGHTLY: yes
-  PIPELINE_USAGE_CUTOFF: 5000
-  SLACK_API_TOKEN: ${{ secrets.SLACK_CIFEEDBACK_BOT_TOKEN }}
 
 jobs:
-  setup_torch_cuda_pipeline_matrix:
-    name: Setup Torch Pipelines Matrix
-    runs-on: ubuntu-latest
-    outputs:
-      pipeline_test_matrix: ${{ steps.fetch_pipeline_matrix.outputs.pipeline_test_matrix }}
-    steps:
-      - name: Checkout diffusers
-        uses: actions/checkout@v3
-        with:
-          fetch-depth: 2
-      - name: Set up Python
-        uses: actions/setup-python@v4
-        with:
-          python-version: "3.8"
-      - name: Install dependencies
-        run: |
-          pip install -e .
-          pip install huggingface_hub
-      - name: Fetch Pipeline Matrix
-        id: fetch_pipeline_matrix
-        run: |
-          matrix=$(python utils/fetch_torch_cuda_pipeline_test_matrix.py)
-          echo $matrix
-          echo "pipeline_test_matrix=$matrix" >> $GITHUB_OUTPUT
-
-      - name: Pipeline Tests Artifacts
-        if: ${{ always() }}
-        uses: actions/upload-artifact@v2
-        with:
-          name: test-pipelines.json
-          path: reports
-
-  run_nightly_tests_for_torch_pipelines:
-    name: Torch Pipelines CUDA Nightly Tests
-    needs: setup_torch_cuda_pipeline_matrix
+  run_nightly_tests:
     strategy:
       fail-fast: false
       matrix:
-        module: ${{ fromJson(needs.setup_torch_cuda_pipeline_matrix.outputs.pipeline_test_matrix) }}
-    runs-on: [single-gpu, nvidia-gpu, t4, ci]
+        config:
+          - name: Nightly PyTorch CUDA tests on Ubuntu
+            framework: pytorch
+            runner: docker-gpu
+            image: diffusers/diffusers-pytorch-cuda
+            report: torch_cuda
+          - name: Nightly Flax TPU tests on Ubuntu
+            framework: flax
+            runner: docker-tpu
+            image: diffusers/diffusers-flax-tpu
+            report: flax_tpu
+          - name: Nightly ONNXRuntime CUDA tests on Ubuntu
+            framework: onnxruntime
+            runner: docker-gpu
+            image: diffusers/diffusers-onnxruntime-cuda
+            report: onnx_cuda
+
+    name: ${{ matrix.config.name }}
+
+    runs-on: ${{ matrix.config.runner }}
+
     container:
-      image: diffusers/diffusers-pytorch-cuda
-      options: --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/ --gpus 0
+      image: ${{ matrix.config.image }}
+      options: --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/ ${{ matrix.config.runner == 'docker-tpu' && '--privileged' || '--gpus 0'}}
+
+    defaults:
+      run:
+        shell: bash
+
     steps:
       - name: Checkout diffusers
         uses: actions/checkout@v3
         with:
           fetch-depth: 2
+
       - name: NVIDIA-SMI
-        run: nvidia-smi
-      
+        if: ${{ matrix.config.runner == 'docker-gpu' }}
+        run: |
+          nvidia-smi
+
       - name: Install dependencies
         run: |
-          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-          python -m uv pip install -e [quality,test]
-          python -m uv pip install accelerate@git+https://github.com/huggingface/accelerate.git
-          python -m uv pip install pytest-reportlog
-      
+          python -m pip install -e .[quality,test]
+          python -m pip install -U git+https://github.com/huggingface/transformers
+          python -m pip install git+https://github.com/huggingface/accelerate
+
       - name: Environment
         run: |
           python utils/print_env.py
-      
-      - name: Nightly PyTorch CUDA checkpoint (pipelines) tests 
+
+      - name: Run nightly PyTorch CUDA tests
+        if: ${{ matrix.config.framework == 'pytorch' }}
         env:
           HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
-          # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
-          CUBLAS_WORKSPACE_CONFIG: :16:8
         run: |
           python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
             -s -v -k "not Flax and not Onnx" \
-            --make-reports=tests_pipeline_${{ matrix.module }}_cuda \
-            --report-log=tests_pipeline_${{ matrix.module }}_cuda.log \ 
-            tests/pipelines/${{ matrix.module }}
-      
+            --make-reports=tests_${{ matrix.config.report }} \
+            tests/
+
+      - name: Run nightly Flax TPU tests
+        if: ${{ matrix.config.framework == 'flax' }}
+        env:
+          HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
+        run: |
+          python -m pytest -n 0 \
+            -s -v -k "Flax" \
+            --make-reports=tests_${{ matrix.config.report }} \
+            tests/
+
+      - name: Run nightly ONNXRuntime CUDA tests
+        if: ${{ matrix.config.framework == 'onnxruntime' }}
+        env:
+          HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
+        run: |
+          python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
+            -s -v -k "Onnx" \
+            --make-reports=tests_${{ matrix.config.report }} \
+            tests/
+
       - name: Failure short reports
         if: ${{ failure() }}
-        run: |
-          cat reports/tests_pipeline_${{ matrix.module }}_cuda_stats.txt
-          cat reports/tests_pipeline_${{ matrix.module }}_cuda_failures_short.txt
+        run: cat reports/tests_${{ matrix.config.report }}_failures_short.txt
 
       - name: Test suite reports artifacts
         if: ${{ always() }}
         uses: actions/upload-artifact@v2
         with:
-          name: pipeline_${{ matrix.module }}_test_reports
+          name: ${{ matrix.config.report }}_test_reports
           path: reports
-      
-      - name: Generate Report and Notify Channel
-        if: always()
-        run: |
-          pip install slack_sdk tabulate
-          python scripts/log_reports.py >> $GITHUB_STEP_SUMMARY
-
-  run_nightly_tests_for_other_torch_modules:
-    name: Torch Non-Pipelines CUDA Nightly Tests
-    runs-on: docker-gpu
-    container:
-      image: diffusers/diffusers-pytorch-cuda
-      options: --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/ --gpus 0
-    defaults:
-      run:
-        shell: bash
-    strategy:
-      matrix:
-        module: [models, schedulers, others, examples]
-    steps:
-    - name: Checkout diffusers
-      uses: actions/checkout@v3
-      with:
-        fetch-depth: 2
-
-    - name: Install dependencies
-      run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m uv pip install -e [quality,test]
-        python -m uv pip install accelerate@git+https://github.com/huggingface/accelerate.git
-        python -m uv pip install pytest-reportlog
-
-    - name: Environment
-      run: python utils/print_env.py
-
-    - name: Run nightly PyTorch CUDA tests for non-pipeline modules
-      if: ${{ matrix.module != 'examples'}} 
-      env:
-        HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
-        # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
-        CUBLAS_WORKSPACE_CONFIG: :16:8
-      run: |
-        python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-          -s -v -k "not Flax and not Onnx" \
-          --make-reports=tests_torch_${{ matrix.module }}_cuda \
-          --report-log=tests_torch_${{ matrix.module }}_cuda.log \ 
-          tests/${{ matrix.module }}
-
-    - name: Run nightly example tests with Torch
-      if: ${{ matrix.module == 'examples' }}
-      env:
-        HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
-        # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
-        CUBLAS_WORKSPACE_CONFIG: :16:8
-      run: |
-        python -m uv pip install peft@git+https://github.com/huggingface/peft.git
-        python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-          -s -v --make-reports=examples_torch_cuda \
-          --report-log=examples_torch_cuda.log \ 
-          examples/
-
-    - name: Failure short reports
-      if: ${{ failure() }}
-      run: |
-        cat reports/tests_torch_${{ matrix.module }}_cuda_stats.txt 
-        cat reports/tests_torch_${{ matrix.module }}_cuda_failures_short.txt
-
-    - name: Test suite reports artifacts
-      if: ${{ always() }}
-      uses: actions/upload-artifact@v2
-      with:
-        name: torch_${{ matrix.module }}_cuda_test_reports
-        path: reports
-
-    - name: Generate Report and Notify Channel
-      if: always()
-      run: |
-        pip install slack_sdk tabulate
-        python scripts/log_reports.py >> $GITHUB_STEP_SUMMARY
-
-  run_lora_nightly_tests:
-    name: Nightly LoRA Tests with PEFT and TORCH
-    runs-on: docker-gpu
-    container:
-      image: diffusers/diffusers-pytorch-cuda
-      options: --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/ --gpus 0
-    defaults:
-      run:
-        shell: bash
-    steps:
-    - name: Checkout diffusers
-      uses: actions/checkout@v3
-      with:
-        fetch-depth: 2
-
-    - name: Install dependencies
-      run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m uv pip install -e [quality,test]
-        python -m uv pip install accelerate@git+https://github.com/huggingface/accelerate.git
-        python -m uv pip install peft@git+https://github.com/huggingface/peft.git
-        python -m uv pip install pytest-reportlog
-
-    - name: Environment
-      run: python utils/print_env.py
-
-    - name: Run nightly LoRA tests with PEFT and Torch
-      env:
-        HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
-        # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
-        CUBLAS_WORKSPACE_CONFIG: :16:8
-      run: |
-        python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-          -s -v -k "not Flax and not Onnx" \
-          --make-reports=tests_torch_lora_cuda \
-          --report-log=tests_torch_lora_cuda.log \ 
-          tests/lora
-    
-    - name: Failure short reports
-      if: ${{ failure() }}
-      run: |
-        cat reports/tests_torch_lora_cuda_stats.txt 
-        cat reports/tests_torch_lora_cuda_failures_short.txt
-
-    - name: Test suite reports artifacts
-      if: ${{ always() }}
-      uses: actions/upload-artifact@v2
-      with:
-        name: torch_lora_cuda_test_reports
-        path: reports
-
-    - name: Generate Report and Notify Channel
-      if: always()
-      run: |
-        pip install slack_sdk tabulate
-        python scripts/log_reports.py >> $GITHUB_STEP_SUMMARY
-  
-  run_flax_tpu_tests:
-    name: Nightly Flax TPU Tests
-    runs-on: docker-tpu
-    if: github.event_name == 'schedule'
-    
-    container:
-      image: diffusers/diffusers-flax-tpu
-      options: --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/ --privileged
-    defaults:
-      run:
-        shell: bash
-    steps:
-    - name: Checkout diffusers
-      uses: actions/checkout@v3
-      with:
-        fetch-depth: 2
-
-    - name: Install dependencies
-      run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m uv pip install -e [quality,test]
-        python -m uv pip install accelerate@git+https://github.com/huggingface/accelerate.git
-        python -m uv pip install pytest-reportlog
-
-    - name: Environment
-      run: python utils/print_env.py
-
-    - name: Run nightly Flax TPU tests
-      env:
-        HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
-      run: |
-        python -m pytest -n 0 \
-          -s -v -k "Flax" \
-          --make-reports=tests_flax_tpu \
-          --report-log=tests_flax_tpu.log \ 
-          tests/
-
-    - name: Failure short reports
-      if: ${{ failure() }}
-      run: |
-        cat reports/tests_flax_tpu_stats.txt
-        cat reports/tests_flax_tpu_failures_short.txt
-
-    - name: Test suite reports artifacts
-      if: ${{ always() }}
-      uses: actions/upload-artifact@v2
-      with:
-        name: flax_tpu_test_reports
-        path: reports
-
-    - name: Generate Report and Notify Channel
-      if: always()
-      run: |
-        pip install slack_sdk tabulate
-        python scripts/log_reports.py >> $GITHUB_STEP_SUMMARY
-
-  run_nightly_onnx_tests:
-    name: Nightly ONNXRuntime CUDA tests on Ubuntu
-    runs-on: docker-gpu
-    container:
-      image: diffusers/diffusers-onnxruntime-cuda
-      options: --gpus 0 --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/
-    
-    steps:
-    - name: Checkout diffusers
-      uses: actions/checkout@v3
-      with:
-        fetch-depth: 2
-
-    - name: NVIDIA-SMI
-      run: nvidia-smi
-
-    - name: Install dependencies
-      run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m uv pip install -e [quality,test]
-        python -m uv pip install accelerate@git+https://github.com/huggingface/accelerate.git
-        python -m uv pip install pytest-reportlog
-
-    - name: Environment
-      run: python utils/print_env.py
-    
-    - name: Run nightly ONNXRuntime CUDA tests
-      env:
-        HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
-      run: |
-        python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-          -s -v -k "Onnx" \
-          --make-reports=tests_onnx_cuda \
-          --report-log=tests_onnx_cuda.log \ 
-          tests/
-
-    - name: Failure short reports
-      if: ${{ failure() }}
-      run: |
-        cat reports/tests_onnx_cuda_stats.txt
-        cat reports/tests_onnx_cuda_failures_short.txt
-
-    - name: Test suite reports artifacts
-      if: ${{ always() }}
-      uses: actions/upload-artifact@v2
-      with:
-        name: ${{ matrix.config.report }}_test_reports
-        path: reports
-    
-    - name: Generate Report and Notify Channel
-      if: always()
-      run: |
-        pip install slack_sdk tabulate
-        python scripts/log_reports.py >> $GITHUB_STEP_SUMMARY
 
   run_nightly_tests_apple_m1:
     name: Nightly PyTorch MPS tests on MacOS
     runs-on: [ self-hosted, apple-m1 ]
-    if: github.event_name == 'schedule'
 
     steps:
       - name: Checkout diffusers
@@ -375,11 +132,10 @@ jobs:
       - name: Install dependencies
         shell: arch -arch arm64 bash {0}
         run: |
-          ${CONDA_RUN} python -m pip install --upgrade pip uv
-          ${CONDA_RUN} python -m uv pip install -e [quality,test]
-          ${CONDA_RUN} python -m uv pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cpu
-          ${CONDA_RUN} python -m uv pip install accelerate@git+https://github.com/huggingface/accelerate
-          ${CONDA_RUN} python -m uv pip install pytest-reportlog
+          ${CONDA_RUN} python -m pip install --upgrade pip
+          ${CONDA_RUN} python -m pip install -e .[quality,test]
+          ${CONDA_RUN} python -m pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cpu
+          ${CONDA_RUN} python -m pip install git+https://github.com/huggingface/accelerate
 
       - name: Environment
         shell: arch -arch arm64 bash {0}
@@ -392,9 +148,7 @@ jobs:
           HF_HOME: /System/Volumes/Data/mnt/cache
           HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
         run: |
-          ${CONDA_RUN} python -m pytest -n 1 -s -v --make-reports=tests_torch_mps \
-            --report-log=tests_torch_mps.log \
-            tests/
+          ${CONDA_RUN} python -m pytest -n 1 -s -v --make-reports=tests_torch_mps tests/
 
       - name: Failure short reports
         if: ${{ failure() }}
@@ -406,9 +160,3 @@ jobs:
         with:
           name: torch_mps_test_reports
           path: reports
-
-      - name: Generate Report and Notify Channel
-        if: always()
-        run: |
-          pip install slack_sdk tabulate
-          python scripts/log_reports.py >> $GITHUB_STEP_SUMMARY

.github/workflows/notify_slack_about_release.yml

@@ -1,23 +0,0 @@
-name: Notify Slack about a release
-
-on:
-  workflow_dispatch:
-  release:
-    types: [published]
-
-jobs:
-  build:
-    runs-on: ubuntu-latest
-
-    steps:
-    - uses: actions/checkout@v3
-    
-    - name: Setup Python
-      uses: actions/setup-python@v4
-      with:
-        python-version: '3.8'
-    
-    - name: Notify Slack about the release
-      env:
-        SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL }}
-      run: pip install requests && python utils/notify_slack_about_release.py

.github/workflows/pr_dependency_test.yml

@@ -4,8 +4,6 @@ on:
   pull_request:
     branches:
       - main
-    paths:
-      - "src/diffusers/**.py"
   push:
     branches:
       - main
@@ -25,12 +23,10 @@ jobs:
           python-version: "3.8"
       - name: Install dependencies
         run: |
-          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-          python -m pip install --upgrade pip uv
-          python -m uv pip install -e .
-          python -m uv pip install pytest
+          python -m pip install --upgrade pip
+          pip install -e .
+          pip install pytest
       - name: Check for soft dependencies
         run: |
-          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
           pytest tests/others/test_dependencies.py
       

.github/workflows/pr_flax_dependency_test.yml

@@ -4,8 +4,6 @@ on:
   pull_request:
     branches:
       - main
-    paths:
-      - "src/diffusers/**.py"
   push:
     branches:
       - main
@@ -25,14 +23,12 @@ jobs:
           python-version: "3.8"
       - name: Install dependencies
         run: |
-          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-          python -m pip install --upgrade pip uv
-          python -m uv pip install -e .
-          python -m uv pip install "jax[cpu]>=0.2.16,!=0.3.2"
-          python -m uv pip install "flax>=0.4.1"
-          python -m uv pip install "jaxlib>=0.1.65"
-          python -m uv pip install pytest
+          python -m pip install --upgrade pip
+          pip install -e .
+          pip install "jax[cpu]>=0.2.16,!=0.3.2"
+          pip install "flax>=0.4.1"
+          pip install "jaxlib>=0.1.65"
+          pip install pytest
       - name: Check for soft dependencies
         run: |
-          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
           pytest tests/others/test_dependencies.py

.github/workflows/pr_quality.yml

@@ -0,0 +1,49 @@
+name: Run code quality checks
+
+on:
+  pull_request:
+    branches:
+      - main
+  push:
+    branches:
+      - main
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}
+  cancel-in-progress: true
+
+jobs:
+  check_code_quality:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.8"
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install .[quality]
+      - name: Check quality
+        run: |
+          ruff check examples tests src utils scripts
+          ruff format examples tests src utils scripts --check
+
+  check_repository_consistency:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.8"
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install .[quality]
+      - name: Check quality
+        run: |
+          python utils/check_copies.py
+          python utils/check_dummies.py
+          make deps_table_check_updated

.github/workflows/pr_test_fetcher.yml

@@ -32,8 +32,8 @@ jobs:
         fetch-depth: 0
     - name: Install dependencies
       run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m uv pip install -e [quality,test]
+        apt-get update && apt-get install libsndfile1-dev libgl1 -y
+        python -m pip install -e .[quality,test]
     - name: Environment
       run: |
         python utils/print_env.py
@@ -88,18 +88,16 @@ jobs:
 
     - name: Install dependencies
       run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m pip install -e [quality,test]
+        apt-get update && apt-get install libsndfile1-dev libgl1 -y
+        python -m pip install -e .[quality,test]
         python -m pip install accelerate
 
     - name: Environment
       run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
         python utils/print_env.py
 
     - name: Run all selected tests on CPU
       run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
         python -m pytest -n 2 --dist=loadfile -v --make-reports=${{ matrix.modules }}_tests_cpu ${{ fromJson(needs.setup_pr_tests.outputs.test_map)[matrix.modules] }}
 
     - name: Failure short reports
@@ -145,18 +143,16 @@ jobs:
 
     - name: Install dependencies
       run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m pip install -e [quality,test]
+        apt-get update && apt-get install libsndfile1-dev libgl1 -y
+        python -m pip install -e .[quality,test]
 
     - name: Environment
       run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
         python utils/print_env.py
 
     - name: Run Hub tests for models, schedulers, and pipelines on a staging env
       if: ${{ matrix.config.framework == 'hub_tests_pytorch' }}
       run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
         HUGGINGFACE_CO_STAGING=true python -m pytest \
           -m "is_staging_test" \
           --make-reports=tests_${{ matrix.config.report }} \

.github/workflows/pr_test_peft_backend.yml

@@ -4,9 +4,6 @@ on:
   pull_request:
     branches:
       - main
-    paths:
-      - "src/diffusers/**.py"
-      - "tests/**.py"
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}
@@ -19,50 +16,7 @@ env:
   PYTEST_TIMEOUT: 60
 
 jobs:
-  check_code_quality:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v3
-      - name: Set up Python
-        uses: actions/setup-python@v4
-        with:
-          python-version: "3.8"
-      - name: Install dependencies
-        run: |
-          python -m pip install --upgrade pip
-          pip install .[quality]
-      - name: Check quality
-        run: make quality
-      - name: Check if failure
-        if: ${{ failure() }}
-        run: |
-          echo "Quality check failed. Please ensure the right dependency versions are installed with 'pip install -e .[quality]' and run 'make style && make quality'" >> $GITHUB_STEP_SUMMARY
-
-  check_repository_consistency:
-    needs: check_code_quality
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v3
-      - name: Set up Python
-        uses: actions/setup-python@v4
-        with:
-          python-version: "3.8"
-      - name: Install dependencies
-        run: |
-          python -m pip install --upgrade pip
-          pip install .[quality]
-      - name: Check repo consistency
-        run: |
-          python utils/check_copies.py
-          python utils/check_dummies.py
-          make deps_table_check_updated
-      - name: Check if failure
-        if: ${{ failure() }}
-        run: |
-          echo "Repo consistency check failed. Please ensure the right dependency versions are installed with 'pip install -e .[quality]' and run 'make fix-copies'" >> $GITHUB_STEP_SUMMARY
-
   run_fast_tests:
-    needs: [check_code_quality, check_repository_consistency]
     strategy:
       fail-fast: false
       matrix:
@@ -71,7 +25,7 @@ jobs:
 
     name: LoRA - ${{ matrix.lib-versions }}
 
-    runs-on: [ self-hosted, intel-cpu, 8-cpu, ci ]
+    runs-on: docker-cpu
 
     container:
       image: diffusers/diffusers-pytorch-cpu
@@ -89,25 +43,23 @@ jobs:
 
     - name: Install dependencies
       run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m uv pip install -e [quality,test]
+        apt-get update && apt-get install libsndfile1-dev libgl1 -y
+        python -m pip install -e .[quality,test]
         if [ "${{ matrix.lib-versions }}" == "main" ]; then
-            python -m pip install -U peft@git+https://github.com/huggingface/peft.git
-            python -m uv pip install -U transformers@git+https://github.com/huggingface/transformers.git
-            python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
+            python -m pip install -U git+https://github.com/huggingface/peft.git
+            python -m pip install -U git+https://github.com/huggingface/transformers.git
+            python -m pip install -U git+https://github.com/huggingface/accelerate.git
         else
-            python -m uv pip install -U peft transformers accelerate
+            python -m pip install -U peft transformers accelerate
         fi
 
     - name: Environment
       run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
         python utils/print_env.py
 
     - name: Run fast PyTorch LoRA CPU tests with PEFT backend
       run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m pytest -n 4 --max-worker-restart=0 --dist=loadfile \
+        python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
           -s -v \
           --make-reports=tests_${{ matrix.config.report }} \
-          tests/lora/
+          tests/lora/test_lora_layers_peft.py

.github/workflows/pr_tests.yml

@@ -4,14 +4,6 @@ on:
   pull_request:
     branches:
       - main
-    paths:
-      - "src/diffusers/**.py"
-      - "benchmarks/**.py"
-      - "examples/**.py"
-      - "scripts/**.py"
-      - "tests/**.py"
-      - ".github/**.yml"
-      - "utils/**.py"
   push:
     branches:
       - ci-*
@@ -27,72 +19,29 @@ env:
   PYTEST_TIMEOUT: 60
 
 jobs:
-  check_code_quality:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v3
-      - name: Set up Python
-        uses: actions/setup-python@v4
-        with:
-          python-version: "3.8"
-      - name: Install dependencies
-        run: |
-          python -m pip install --upgrade pip
-          pip install .[quality]
-      - name: Check quality
-        run: make quality
-      - name: Check if failure
-        if: ${{ failure() }}
-        run: |
-          echo "Quality check failed. Please ensure the right dependency versions are installed with 'pip install -e .[quality]' and run 'make style && make quality'" >> $GITHUB_STEP_SUMMARY
-
-  check_repository_consistency:
-    needs: check_code_quality
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v3
-      - name: Set up Python
-        uses: actions/setup-python@v4
-        with:
-          python-version: "3.8"
-      - name: Install dependencies
-        run: |
-          python -m pip install --upgrade pip
-          pip install .[quality]
-      - name: Check repo consistency
-        run: |
-          python utils/check_copies.py
-          python utils/check_dummies.py
-          make deps_table_check_updated
-      - name: Check if failure
-        if: ${{ failure() }}
-        run: |
-          echo "Repo consistency check failed. Please ensure the right dependency versions are installed with 'pip install -e .[quality]' and run 'make fix-copies'" >> $GITHUB_STEP_SUMMARY
-
   run_fast_tests:
-    needs: [check_code_quality, check_repository_consistency]
     strategy:
       fail-fast: false
       matrix:
         config:
           - name: Fast PyTorch Pipeline CPU tests
             framework: pytorch_pipelines
-            runner: [ self-hosted, intel-cpu, 32-cpu, 256-ram, ci ]
+            runner: docker-cpu
             image: diffusers/diffusers-pytorch-cpu
             report: torch_cpu_pipelines
           - name: Fast PyTorch Models & Schedulers CPU tests
             framework: pytorch_models
-            runner: [ self-hosted, intel-cpu, 8-cpu, ci ]
+            runner: docker-cpu
             image: diffusers/diffusers-pytorch-cpu
             report: torch_cpu_models_schedulers
           - name: Fast Flax CPU tests
             framework: flax
-            runner: [ self-hosted, intel-cpu, 8-cpu, ci ]
+            runner: docker-cpu
             image: diffusers/diffusers-flax-cpu
             report: flax_cpu
           - name: PyTorch Example CPU tests
             framework: pytorch_examples
-            runner: [ self-hosted, intel-cpu, 8-cpu, ci ]
+            runner: docker-cpu
             image: diffusers/diffusers-pytorch-cpu
             report: torch_example_cpu
 
@@ -116,20 +65,18 @@ jobs:
 
     - name: Install dependencies
       run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m uv pip install -e [quality,test]
-        python -m uv pip install accelerate
+        apt-get update && apt-get install libsndfile1-dev libgl1 -y
+        python -m pip install -e .[quality,test]
+        python -m pip install accelerate
 
     - name: Environment
       run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
         python utils/print_env.py
 
     - name: Run fast PyTorch Pipeline CPU tests
       if: ${{ matrix.config.framework == 'pytorch_pipelines' }}
       run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m pytest -n 8 --max-worker-restart=0 --dist=loadfile \
+        python -m pytest -n 2 --max-worker-restart=0 --dist=loadfile \
           -s -v -k "not Flax and not Onnx" \
           --make-reports=tests_${{ matrix.config.report }} \
           tests/pipelines
@@ -137,8 +84,7 @@ jobs:
     - name: Run fast PyTorch Model Scheduler CPU tests
       if: ${{ matrix.config.framework == 'pytorch_models' }}
       run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m pytest -n 4 --max-worker-restart=0 --dist=loadfile \
+        python -m pytest -n 2 --max-worker-restart=0 --dist=loadfile \
           -s -v -k "not Flax and not Onnx and not Dependency" \
           --make-reports=tests_${{ matrix.config.report }} \
           tests/models tests/schedulers tests/others
@@ -146,8 +92,7 @@ jobs:
     - name: Run fast Flax TPU tests
       if: ${{ matrix.config.framework == 'flax' }}
       run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m pytest -n 4 --max-worker-restart=0 --dist=loadfile \
+        python -m pytest -n 2 --max-worker-restart=0 --dist=loadfile \
           -s -v -k "Flax" \
           --make-reports=tests_${{ matrix.config.report }} \
           tests
@@ -155,9 +100,8 @@ jobs:
     - name: Run example PyTorch CPU tests
       if: ${{ matrix.config.framework == 'pytorch_examples' }}
       run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m uv pip install peft
-        python -m pytest -n 4 --max-worker-restart=0 --dist=loadfile \
+        python -m pip install peft
+        python -m pytest -n 2 --max-worker-restart=0 --dist=loadfile \
           --make-reports=tests_${{ matrix.config.report }} \
           examples
 
@@ -173,14 +117,13 @@ jobs:
         path: reports
 
   run_staging_tests:
-    needs: [check_code_quality, check_repository_consistency]
     strategy:
       fail-fast: false
       matrix:
         config:
           - name: Hub tests for models, schedulers, and pipelines
             framework: hub_tests_pytorch
-            runner: [ self-hosted, intel-cpu, 8-cpu, ci ]
+            runner: docker-cpu
             image: diffusers/diffusers-pytorch-cpu
             report: torch_hub
 
@@ -204,18 +147,16 @@ jobs:
 
     - name: Install dependencies
       run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m uv pip install -e [quality,test]
+        apt-get update && apt-get install libsndfile1-dev libgl1 -y
+        python -m pip install -e .[quality,test]
 
     - name: Environment
       run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
         python utils/print_env.py
 
     - name: Run Hub tests for models, schedulers, and pipelines on a staging env
       if: ${{ matrix.config.framework == 'hub_tests_pytorch' }}
       run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
         HUGGINGFACE_CO_STAGING=true python -m pytest \
           -m "is_staging_test" \
           --make-reports=tests_${{ matrix.config.report }} \

.github/workflows/pr_torch_dependency_test.yml

@@ -4,8 +4,6 @@ on:
   pull_request:
     branches:
       - main
-    paths:
-      - "src/diffusers/**.py"
   push:
     branches:
       - main
@@ -25,12 +23,10 @@ jobs:
           python-version: "3.8"
       - name: Install dependencies
         run: |
-          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-          python -m pip install --upgrade pip uv
-          python -m uv pip install -e .
-          python -m uv pip install torch torchvision torchaudio
-          python -m uv pip install pytest
+          python -m pip install --upgrade pip
+          pip install -e .
+          pip install torch torchvision torchaudio
+          pip install pytest
       - name: Check for soft dependencies
         run: |
-          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
           pytest tests/others/test_dependencies.py

.github/workflows/push_tests.yml

@@ -4,10 +4,7 @@ on:
   push:
     branches:
       - main
-    paths:
-      - "src/diffusers/**.py"
-      - "examples/**.py"
-      - "tests/**.py"
+
 
 env:
   DIFFUSERS_IS_CI: yes
@@ -21,7 +18,10 @@ env:
 jobs:
   setup_torch_cuda_pipeline_matrix:
     name: Setup Torch Pipelines CUDA Slow Tests Matrix
-    runs-on: ubuntu-latest
+    runs-on: docker-gpu
+    container:
+      image: diffusers/diffusers-pytorch-cpu # this is a CPU image, but we need it to fetch the matrix
+      options: --shm-size "16gb" --ipc host
     outputs:
       pipeline_test_matrix: ${{ steps.fetch_pipeline_matrix.outputs.pipeline_test_matrix }}
     steps:
@@ -29,20 +29,23 @@ jobs:
         uses: actions/checkout@v3
         with:
           fetch-depth: 2
-      - name: Set up Python
-        uses: actions/setup-python@v4
-        with:
-          python-version: "3.8"
       - name: Install dependencies
         run: |
-          pip install -e .
-          pip install huggingface_hub
+          apt-get update && apt-get install libsndfile1-dev libgl1 -y
+          python -m pip install -e .[quality,test]
+          python -m pip install git+https://github.com/huggingface/accelerate.git
+
+      - name: Environment
+        run: |
+          python utils/print_env.py
+
       - name: Fetch Pipeline Matrix
         id: fetch_pipeline_matrix
         run: |
           matrix=$(python utils/fetch_torch_cuda_pipeline_test_matrix.py)
           echo $matrix
           echo "pipeline_test_matrix=$matrix" >> $GITHUB_OUTPUT
+
       - name: Pipeline Tests Artifacts
         if: ${{ always() }}
         uses: actions/upload-artifact@v2
@@ -55,12 +58,13 @@ jobs:
     needs: setup_torch_cuda_pipeline_matrix
     strategy:
       fail-fast: false
+      max-parallel: 1
       matrix:
         module: ${{ fromJson(needs.setup_torch_cuda_pipeline_matrix.outputs.pipeline_test_matrix) }}
-    runs-on: [single-gpu, nvidia-gpu, t4, ci]
+    runs-on: docker-gpu
     container:
       image: diffusers/diffusers-pytorch-cuda
-      options: --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/ --gpus 0 --privileged
+      options: --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/ --gpus 0
     steps:
       - name: Checkout diffusers
         uses: actions/checkout@v3
@@ -69,17 +73,11 @@ jobs:
       - name: NVIDIA-SMI
         run: |
           nvidia-smi
-      - name: Tailscale
-        uses: huggingface/tailscale-action@v1
-        with:
-          authkey: ${{ secrets.TAILSCALE_SSH_AUTHKEY }}
-          slackChannel: ${{ secrets.SLACK_CIFEEDBACK_CHANNEL }}
-          slackToken: ${{ secrets.SLACK_CIFEEDBACK_BOT_TOKEN }}
       - name: Install dependencies
         run: |
-          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-          python -m uv pip install -e [quality,test]
-          python -m uv pip install accelerate@git+https://github.com/huggingface/accelerate.git
+          apt-get update && apt-get install libsndfile1-dev libgl1 -y
+          python -m pip install -e .[quality,test]
+          python -m pip install git+https://github.com/huggingface/accelerate.git
       - name: Environment
         run: |
           python utils/print_env.py
@@ -93,12 +91,6 @@ jobs:
             -s -v -k "not Flax and not Onnx" \
             --make-reports=tests_pipeline_${{ matrix.module }}_cuda \
             tests/pipelines/${{ matrix.module }}
-      - name: Tailscale Wait
-        if: ${{ failure() || runner.debug == '1' }}
-        uses: huggingface/tailscale-action@v1
-        with:
-           waitForSSH: true
-           authkey: ${{ secrets.TAILSCALE_SSH_AUTHKEY }}
       - name: Failure short reports
         if: ${{ failure() }}
         run: |
@@ -132,9 +124,9 @@ jobs:
 
     - name: Install dependencies
       run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m uv pip install -e [quality,test]
-        python -m uv pip install accelerate@git+https://github.com/huggingface/accelerate.git
+        apt-get update && apt-get install libsndfile1-dev libgl1 -y
+        python -m pip install -e .[quality,test]
+        python -m pip install git+https://github.com/huggingface/accelerate.git
 
     - name: Environment
       run: |
@@ -181,10 +173,10 @@ jobs:
 
     - name: Install dependencies
       run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m uv pip install -e [quality,test]
-        python -m uv pip install accelerate@git+https://github.com/huggingface/accelerate.git
-        python -m pip install -U peft@git+https://github.com/huggingface/peft.git
+        apt-get update && apt-get install libsndfile1-dev libgl1 -y
+        python -m pip install -e .[quality,test]
+        python -m pip install git+https://github.com/huggingface/accelerate.git
+        python -m pip install git+https://github.com/huggingface/peft.git
 
     - name: Environment
       run: |
@@ -231,9 +223,9 @@ jobs:
 
     - name: Install dependencies
       run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m uv pip install -e [quality,test]
-        python -m uv pip install accelerate@git+https://github.com/huggingface/accelerate.git
+        apt-get update && apt-get install libsndfile1-dev libgl1 -y
+        python -m pip install -e .[quality,test]
+        python -m pip install git+https://github.com/huggingface/accelerate.git
 
     - name: Environment
       run: |
@@ -278,9 +270,9 @@ jobs:
 
     - name: Install dependencies
       run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m uv pip install -e [quality,test]
-        python -m uv pip install accelerate@git+https://github.com/huggingface/accelerate.git
+        apt-get update && apt-get install libsndfile1-dev libgl1 -y
+        python -m pip install -e .[quality,test]
+        python -m pip install git+https://github.com/huggingface/accelerate.git
 
     - name: Environment
       run: |
@@ -328,8 +320,7 @@ jobs:
         nvidia-smi
     - name: Install dependencies
       run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m uv pip install -e [quality,test,training]
+        python -m pip install -e .[quality,test,training]
     - name: Environment
       run: |
         python utils/print_env.py
@@ -369,8 +360,7 @@ jobs:
         nvidia-smi
     - name: Install dependencies
       run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m uv pip install -e [quality,test,training]
+        python -m pip install -e .[quality,test,training]
     - name: Environment
       run: |
         python utils/print_env.py
@@ -411,19 +401,16 @@ jobs:
 
     - name: Install dependencies
       run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m uv pip install -e [quality,test,training]
+        python -m pip install -e .[quality,test,training]
 
     - name: Environment
       run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
         python utils/print_env.py
 
     - name: Run example tests on GPU
       env:
         HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
       run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
         python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile -s -v --make-reports=examples_torch_cuda examples/
 
     - name: Failure short reports
@@ -437,4 +424,4 @@ jobs:
       uses: actions/upload-artifact@v2
       with:
         name: examples_test_reports
-        path: reports
+        path: reports

.github/workflows/push_tests_fast.yml

@@ -4,10 +4,6 @@ on:
   push:
     branches:
       - main
-    paths:
-      - "src/diffusers/**.py"
-      - "examples/**.py"
-      - "tests/**.py"
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}
@@ -29,22 +25,22 @@ jobs:
         config:
           - name: Fast PyTorch CPU tests on Ubuntu
             framework: pytorch
-            runner: [ self-hosted, intel-cpu, 8-cpu, ci ]
+            runner: docker-cpu
             image: diffusers/diffusers-pytorch-cpu
             report: torch_cpu
           - name: Fast Flax CPU tests on Ubuntu
             framework: flax
-            runner: [ self-hosted, intel-cpu, 8-cpu, ci ]
+            runner: docker-cpu
             image: diffusers/diffusers-flax-cpu
             report: flax_cpu
           - name: Fast ONNXRuntime CPU tests on Ubuntu
             framework: onnxruntime
-            runner: [ self-hosted, intel-cpu, 8-cpu, ci ]
+            runner: docker-cpu
             image: diffusers/diffusers-onnxruntime-cpu
             report: onnx_cpu
           - name: PyTorch Example CPU tests on Ubuntu
             framework: pytorch_examples
-            runner: [ self-hosted, intel-cpu, 8-cpu, ci ]
+            runner: docker-cpu
             image: diffusers/diffusers-pytorch-cpu
             report: torch_example_cpu
 
@@ -68,19 +64,17 @@ jobs:
 
     - name: Install dependencies
       run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m uv pip install -e [quality,test]
+        apt-get update && apt-get install libsndfile1-dev libgl1 -y
+        python -m pip install -e .[quality,test]
 
     - name: Environment
       run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
         python utils/print_env.py
 
     - name: Run fast PyTorch CPU tests
       if: ${{ matrix.config.framework == 'pytorch' }}
       run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m pytest -n 4 --max-worker-restart=0 --dist=loadfile \
+        python -m pytest -n 2 --max-worker-restart=0 --dist=loadfile \
           -s -v -k "not Flax and not Onnx" \
           --make-reports=tests_${{ matrix.config.report }} \
           tests/
@@ -88,8 +82,7 @@ jobs:
     - name: Run fast Flax TPU tests
       if: ${{ matrix.config.framework == 'flax' }}
       run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m pytest -n 4 --max-worker-restart=0 --dist=loadfile \
+        python -m pytest -n 2 --max-worker-restart=0 --dist=loadfile \
           -s -v -k "Flax" \
           --make-reports=tests_${{ matrix.config.report }} \
           tests/
@@ -97,8 +90,7 @@ jobs:
     - name: Run fast ONNXRuntime CPU tests
       if: ${{ matrix.config.framework == 'onnxruntime' }}
       run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m pytest -n 4 --max-worker-restart=0 --dist=loadfile \
+        python -m pytest -n 2 --max-worker-restart=0 --dist=loadfile \
           -s -v -k "Onnx" \
           --make-reports=tests_${{ matrix.config.report }} \
           tests/
@@ -106,9 +98,8 @@ jobs:
     - name: Run example PyTorch CPU tests
       if: ${{ matrix.config.framework == 'pytorch_examples' }}
       run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m uv pip install peft
-        python -m pytest -n 4 --max-worker-restart=0 --dist=loadfile \
+        python -m pip install peft
+        python -m pytest -n 2 --max-worker-restart=0 --dist=loadfile \
           --make-reports=tests_${{ matrix.config.report }} \
           examples
 

.github/workflows/push_tests_mps.yml

@@ -4,9 +4,6 @@ on:
   push:
     branches:
       - main
-    paths:
-      - "src/diffusers/**.py"
-      - "tests/**.py"
 
 env:
   DIFFUSERS_IS_CI: yes
@@ -44,11 +41,11 @@ jobs:
     - name: Install dependencies
       shell: arch -arch arm64 bash {0}
       run: |
-        ${CONDA_RUN} python -m pip install --upgrade pip uv
-        ${CONDA_RUN} python -m uv pip install -e [quality,test]
-        ${CONDA_RUN} python -m uv pip install torch torchvision torchaudio
-        ${CONDA_RUN} python -m uv pip install accelerate@git+https://github.com/huggingface/accelerate.git
-        ${CONDA_RUN} python -m uv pip install transformers --upgrade
+        ${CONDA_RUN} python -m pip install --upgrade pip
+        ${CONDA_RUN} python -m pip install -e .[quality,test]
+        ${CONDA_RUN} python -m pip install torch torchvision torchaudio
+        ${CONDA_RUN} python -m pip install git+https://github.com/huggingface/accelerate.git
+        ${CONDA_RUN} python -m pip install transformers --upgrade
 
     - name: Environment
       shell: arch -arch arm64 bash {0}

.github/workflows/pypi_publish.yaml

@@ -1,81 +0,0 @@
-# Adapted from https://blog.deepjyoti30.dev/pypi-release-github-action
-
-name: PyPI release
-
-on:
-  workflow_dispatch:
-  push:
-    tags:
-      - "*"
-
-jobs:
-  find-and-checkout-latest-branch:
-    runs-on: ubuntu-latest
-    outputs:
-      latest_branch: ${{ steps.set_latest_branch.outputs.latest_branch }}
-    steps:
-      - name: Checkout Repo
-        uses: actions/checkout@v3
-
-      - name: Set up Python
-        uses: actions/setup-python@v4
-        with:
-          python-version: '3.8'
-
-      - name: Fetch latest branch
-        id: fetch_latest_branch
-        run: |
-          pip install -U requests packaging
-          LATEST_BRANCH=$(python utils/fetch_latest_release_branch.py)
-          echo "Latest branch: $LATEST_BRANCH"
-          echo "latest_branch=$LATEST_BRANCH" >> $GITHUB_ENV
-          
-      - name: Set latest branch output
-        id: set_latest_branch
-        run: echo "::set-output name=latest_branch::${{ env.latest_branch }}"
-
-  release:
-    needs: find-and-checkout-latest-branch
-    runs-on: ubuntu-latest
-
-    steps:
-      - name: Checkout Repo
-        uses: actions/checkout@v3
-        with:
-          ref: ${{ needs.find-and-checkout-latest-branch.outputs.latest_branch }}
-          
-      - name: Setup Python
-        uses: actions/setup-python@v4
-        with:
-          python-version: "3.8"
-      
-      - name: Install dependencies
-        run: |
-          python -m pip install --upgrade pip
-          pip install -U setuptools wheel twine
-          pip install -U torch --index-url https://download.pytorch.org/whl/cpu
-          pip install -U transformers
-      
-      - name: Build the dist files
-        run: python setup.py bdist_wheel && python setup.py sdist
-      
-      - name: Publish to the test PyPI
-        env:
-          TWINE_USERNAME: ${{ secrets.TEST_PYPI_USERNAME }}
-          TWINE_PASSWORD: ${{ secrets.TEST_PYPI_PASSWORD }}
-        run: twine upload dist/* -r pypitest --repository-url=https://test.pypi.org/legacy/    
-
-      - name: Test installing diffusers and importing
-        run: |
-          pip install diffusers && pip uninstall diffusers -y
-          pip install -i https://testpypi.python.org/pypi diffusers
-          python -c "from diffusers import __version__; print(__version__)"
-          python -c "from diffusers import DiffusionPipeline; pipe = DiffusionPipeline.from_pretrained('fusing/unet-ldm-dummy-update'); pipe()"
-          python -c "from diffusers import DiffusionPipeline; pipe = DiffusionPipeline.from_pretrained('hf-internal-testing/tiny-stable-diffusion-pipe', safety_checker=None); pipe('ah suh du')"
-          python -c "from diffusers import *"
-
-      - name: Publish to PyPI
-        env:
-          TWINE_USERNAME: ${{ secrets.PYPI_USERNAME }}
-          TWINE_PASSWORD: ${{ secrets.PYPI_PASSWORD }}
-        run: twine upload dist/* -r pypi

.github/workflows/update_metadata.yml

@@ -1,30 +0,0 @@
-name: Update Diffusers metadata
-
-on:
-  workflow_dispatch:
-  push:
-    branches:
-      - main
-      - update_diffusers_metadata*
-
-jobs:
-  update_metadata:
-    runs-on: ubuntu-22.04
-    defaults:
-      run:
-        shell: bash -l {0}
-
-    steps:
-      - uses: actions/checkout@v3
-
-      - name: Setup environment
-        run: |
-          pip install --upgrade pip
-          pip install datasets pandas
-          pip install .[torch]
-
-      - name: Update metadata
-        env:
-          HUGGING_FACE_HUB_TOKEN: ${{ secrets.SAYAK_HF_TOKEN }}
-        run: |
-          python utils/update_metadata.py --commit_sha ${{ github.sha }}

CITATION.cff

@@ -19,16 +19,6 @@ authors:
     family-names: Rasul
   - given-names: Mishig
     family-names: Davaadorj
-  - given-names: Dhruv
-    family-names: Nair
-  - given-names: Sayak
-    family-names: Paul
-  - given-names: Steven
-    family-names: Liu
-  - given-names: William
-    family-names: Berman
-  - given-names: Yiyi
-    family-names: Xu
   - given-names: Thomas
     family-names: Wolf
 repository-code: 'https://github.com/huggingface/diffusers'

Makefile

@@ -42,7 +42,6 @@ repo-consistency:
 quality:
 	ruff check $(check_dirs) setup.py
 	ruff format --check $(check_dirs) setup.py
-	doc-builder style src/diffusers docs/source --max_len 119 --check_only
 	python utils/check_doc_toc.py
 
 # Format source code automatically and check is there are any problems left that need manual fixing
@@ -56,7 +55,6 @@ extra_style_checks:
 style:
 	ruff check $(check_dirs) setup.py --fix
 	ruff format $(check_dirs) setup.py
-	doc-builder style src/diffusers docs/source --max_len 119
 	${MAKE} autogenerate_code
 	${MAKE} extra_style_checks
 

README.md

@@ -77,7 +77,7 @@ Please refer to the [How to use Stable Diffusion in Apple Silicon](https://huggi
 
 ## Quickstart
 
-Generating outputs is super easy with 🤗 Diffusers. To generate an image from text, use the `from_pretrained` method to load any pretrained diffusion model (browse the [Hub](https://huggingface.co/models?library=diffusers&sort=downloads) for 22000+ checkpoints):
+Generating outputs is super easy with 🤗 Diffusers. To generate an image from text, use the `from_pretrained` method to load any pretrained diffusion model (browse the [Hub](https://huggingface.co/models?library=diffusers&sort=downloads) for 19000+ checkpoints):
 
 ```python
 from diffusers import DiffusionPipeline
@@ -219,7 +219,7 @@ Also, say 👋 in our public Discord channel <a href="https://discord.gg/G7tWnz9
 - https://github.com/deep-floyd/IF
 - https://github.com/bentoml/BentoML
 - https://github.com/bmaltais/kohya_ss
-- +9000 other amazing GitHub repositories 💪
+- +8000 other amazing GitHub repositories 💪
 
 Thank you for using us ❤️.
 
@@ -238,7 +238,7 @@ We also want to thank @heejkoo for the very helpful overview of papers, code and
 
 ```bibtex
 @misc{von-platen-etal-2022-diffusers,
-  author = {Patrick von Platen and Suraj Patil and Anton Lozhkov and Pedro Cuenca and Nathan Lambert and Kashif Rasul and Mishig Davaadorj and Dhruv Nair and Sayak Paul and William Berman and Yiyi Xu and Steven Liu and Thomas Wolf},
+  author = {Patrick von Platen and Suraj Patil and Anton Lozhkov and Pedro Cuenca and Nathan Lambert and Kashif Rasul and Mishig Davaadorj and Thomas Wolf},
   title = {Diffusers: State-of-the-art diffusion models},
   year = {2022},
   publisher = {GitHub},

benchmarks/base_classes.py

@@ -141,7 +141,6 @@ class LCMLoRATextToImageBenchmark(TextToImageBenchmark):
         super().__init__(args)
         self.pipe.load_lora_weights(self.lora_id)
         self.pipe.fuse_lora()
-        self.pipe.unload_lora_weights()
         self.pipe.scheduler = LCMScheduler.from_config(self.pipe.scheduler.config)
 
     def get_result_filepath(self, args):
@@ -236,35 +235,6 @@ class InpaintingBenchmark(ImageToImageBenchmark):
         )
 
 
-class IPAdapterTextToImageBenchmark(TextToImageBenchmark):
-    url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/load_neg_embed.png"
-    image = load_image(url)
-
-    def __init__(self, args):
-        pipe = self.pipeline_class.from_pretrained(args.ckpt, torch_dtype=torch.float16).to("cuda")
-        pipe.load_ip_adapter(
-            args.ip_adapter_id[0],
-            subfolder="models" if "sdxl" not in args.ip_adapter_id[1] else "sdxl_models",
-            weight_name=args.ip_adapter_id[1],
-        )
-
-        if args.run_compile:
-            pipe.unet.to(memory_format=torch.channels_last)
-            print("Run torch compile")
-            pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
-
-        pipe.set_progress_bar_config(disable=True)
-        self.pipe = pipe
-
-    def run_inference(self, pipe, args):
-        _ = pipe(
-            prompt=PROMPT,
-            ip_adapter_image=self.image,
-            num_inference_steps=args.num_inference_steps,
-            num_images_per_prompt=args.batch_size,
-        )
-
-
 class ControlNetBenchmark(TextToImageBenchmark):
     pipeline_class = StableDiffusionControlNetPipeline
     aux_network_class = ControlNetModel

benchmarks/benchmark_ip_adapters.py

@@ -1,32 +0,0 @@
-import argparse
-import sys
-
-
-sys.path.append(".")
-from base_classes import IPAdapterTextToImageBenchmark  # noqa: E402
-
-
-IP_ADAPTER_CKPTS = {
-    "runwayml/stable-diffusion-v1-5": ("h94/IP-Adapter", "ip-adapter_sd15.bin"),
-    "stabilityai/stable-diffusion-xl-base-1.0": ("h94/IP-Adapter", "ip-adapter_sdxl.bin"),
-}
-
-
-if __name__ == "__main__":
-    parser = argparse.ArgumentParser()
-    parser.add_argument(
-        "--ckpt",
-        type=str,
-        default="runwayml/stable-diffusion-v1-5",
-        choices=list(IP_ADAPTER_CKPTS.keys()),
-    )
-    parser.add_argument("--batch_size", type=int, default=1)
-    parser.add_argument("--num_inference_steps", type=int, default=50)
-    parser.add_argument("--model_cpu_offload", action="store_true")
-    parser.add_argument("--run_compile", action="store_true")
-    args = parser.parse_args()
-
-    args.ip_adapter_id = IP_ADAPTER_CKPTS[args.ckpt]
-    benchmark_pipe = IPAdapterTextToImageBenchmark(args)
-    args.ckpt = f"{args.ckpt} (IP-Adapter)"
-    benchmark_pipe.benchmark(args)

benchmarks/run_all.py

@@ -72,7 +72,7 @@ def main():
                 command += " --run_compile"
                 run_command(command.split())
 
-        elif file in ["benchmark_sd_inpainting.py", "benchmark_ip_adapters.py"]:
+        elif file == "benchmark_sd_inpainting.py":
             sdxl_ckpt = "stabilityai/stable-diffusion-xl-base-1.0"
             command = f"python {file} --ckpt {sdxl_ckpt}"
             run_command(command.split())

docker/diffusers-flax-cpu/Dockerfile

@@ -12,7 +12,6 @@ RUN apt update && \
                    curl \
                    ca-certificates \
                    libsndfile1-dev \
-                   libgl1 \
                    python3.8 \
                    python3-pip \
                    python3.8-venv && \
@@ -24,13 +23,13 @@ ENV PATH="/opt/venv/bin:$PATH"
 
 # pre-install the heavy dependencies (these can later be overridden by the deps from setup.py)
 # follow the instructions here: https://cloud.google.com/tpu/docs/run-in-container#train_a_jax_model_in_a_docker_container
-RUN python3 -m pip install --no-cache-dir --upgrade pip uv==0.1.11 && \
-    python3 -m uv pip install --upgrade --no-cache-dir \
+RUN python3 -m pip install --no-cache-dir --upgrade pip && \
+    python3 -m pip install --upgrade --no-cache-dir \
         clu \
         "jax[cpu]>=0.2.16,!=0.3.2" \
         "flax>=0.4.1" \
         "jaxlib>=0.1.65" && \
-    python3 -m uv pip install --no-cache-dir \
+    python3 -m pip install --no-cache-dir \
         accelerate \
         datasets \
         hf-doc-builder \

docker/diffusers-flax-tpu/Dockerfile

@@ -12,7 +12,6 @@ RUN apt update && \
                    curl \
                    ca-certificates \
                    libsndfile1-dev \
-                   libgl1 \
                    python3.8 \
                    python3-pip \
                    python3.8-venv && \
@@ -24,15 +23,15 @@ ENV PATH="/opt/venv/bin:$PATH"
 
 # pre-install the heavy dependencies (these can later be overridden by the deps from setup.py)
 # follow the instructions here: https://cloud.google.com/tpu/docs/run-in-container#train_a_jax_model_in_a_docker_container
-RUN python3 -m pip install --no-cache-dir --upgrade pip uv==0.1.11 && \
+RUN python3 -m pip install --no-cache-dir --upgrade pip && \
     python3 -m pip install --no-cache-dir \
         "jax[tpu]>=0.2.16,!=0.3.2" \
         -f https://storage.googleapis.com/jax-releases/libtpu_releases.html && \
-    python3 -m uv pip install --upgrade --no-cache-dir \
+    python3 -m pip install --upgrade --no-cache-dir \
         clu \
         "flax>=0.4.1" \
         "jaxlib>=0.1.65" && \
-    python3 -m uv pip install --no-cache-dir \
+    python3 -m pip install --no-cache-dir \
         accelerate \
         datasets \
         hf-doc-builder \

docker/diffusers-onnxruntime-cpu/Dockerfile

@@ -12,7 +12,6 @@ RUN apt update && \
                    curl \
                    ca-certificates \
                    libsndfile1-dev \
-                   libgl1 \
                    python3.8 \
                    python3-pip \
                    python3.8-venv && \
@@ -23,14 +22,14 @@ RUN python3 -m venv /opt/venv
 ENV PATH="/opt/venv/bin:$PATH"
 
 # pre-install the heavy dependencies (these can later be overridden by the deps from setup.py)
-RUN python3 -m pip install --no-cache-dir --upgrade pip uv==0.1.11 && \
-    python3 -m uv pip install --no-cache-dir \
+RUN python3 -m pip install --no-cache-dir --upgrade pip && \
+    python3 -m pip install --no-cache-dir \
         torch==2.1.2 \
         torchvision==0.16.2 \
         torchaudio==2.1.2 \
         onnxruntime \
         --extra-index-url https://download.pytorch.org/whl/cpu && \
-    python3 -m uv pip install --no-cache-dir \
+    python3 -m pip install --no-cache-dir \
         accelerate \
         datasets \
         hf-doc-builder \

docker/diffusers-onnxruntime-cuda/Dockerfile

@@ -1,4 +1,4 @@
-FROM nvidia/cuda:12.1.0-runtime-ubuntu20.04
+FROM nvidia/cuda:11.6.2-cudnn8-devel-ubuntu20.04
 LABEL maintainer="Hugging Face"
 LABEL repository="diffusers"
 
@@ -12,7 +12,6 @@ RUN apt update && \
                    curl \
                    ca-certificates \
                    libsndfile1-dev \
-                   libgl1 \
                    python3.8 \
                    python3-pip \
                    python3.8-venv && \
@@ -23,14 +22,14 @@ RUN python3 -m venv /opt/venv
 ENV PATH="/opt/venv/bin:$PATH"
 
 # pre-install the heavy dependencies (these can later be overridden by the deps from setup.py)
-RUN python3 -m pip install --no-cache-dir --upgrade pip uv==0.1.11 && \
-    python3 -m uv pip install --no-cache-dir \
-        torch \
-        torchvision \
-        torchaudio \
+RUN python3 -m pip install --no-cache-dir --upgrade pip && \
+    python3 -m pip install --no-cache-dir \
+        torch==2.1.2 \
+        torchvision==0.16.2 \
+        torchaudio==2.1.2 \
         "onnxruntime-gpu>=1.13.1" \
         --extra-index-url https://download.pytorch.org/whl/cu117 && \
-    python3 -m uv pip install --no-cache-dir \
+    python3 -m pip install --no-cache-dir \
         accelerate \
         datasets \
         hf-doc-builder \

docker/diffusers-pytorch-compile-cuda/Dockerfile

@@ -24,8 +24,8 @@ RUN python3.9 -m venv /opt/venv
 ENV PATH="/opt/venv/bin:$PATH"
 
 # pre-install the heavy dependencies (these can later be overridden by the deps from setup.py)
-RUN python3.9 -m pip install --no-cache-dir --upgrade pip uv==0.1.11 && \
-    python3.9 -m uv pip install --no-cache-dir \
+RUN python3.9 -m pip install --no-cache-dir --upgrade pip && \
+    python3.9 -m pip install --no-cache-dir \
     torch \
     torchvision \
     torchaudio \

docker/diffusers-pytorch-cpu/Dockerfile

@@ -23,14 +23,14 @@ RUN python3 -m venv /opt/venv
 ENV PATH="/opt/venv/bin:$PATH"
 
 # pre-install the heavy dependencies (these can later be overridden by the deps from setup.py)
-RUN python3 -m pip install --no-cache-dir --upgrade pip uv==0.1.11 && \
-    python3 -m uv pip install --no-cache-dir \
+RUN python3 -m pip install --no-cache-dir --upgrade pip && \
+    python3 -m pip install --no-cache-dir \
         torch \
         torchvision \
         torchaudio \
         invisible_watermark \
         --extra-index-url https://download.pytorch.org/whl/cpu && \
-    python3 -m uv pip install --no-cache-dir \
+    python3 -m pip install --no-cache-dir \
         accelerate \
         datasets \
         hf-doc-builder \
@@ -40,6 +40,6 @@ RUN python3 -m pip install --no-cache-dir --upgrade pip uv==0.1.11 && \
         numpy \
         scipy \
         tensorboard \
-        transformers matplotlib
+        transformers
 
 CMD ["/bin/bash"]

docker/diffusers-pytorch-cuda/Dockerfile

@@ -23,8 +23,8 @@ RUN python3 -m venv /opt/venv
 ENV PATH="/opt/venv/bin:$PATH"
 
 # pre-install the heavy dependencies (these can later be overridden by the deps from setup.py)
-RUN python3 -m pip install --no-cache-dir --upgrade pip uv==0.1.11 && \
-    python3 -m uv pip install --no-cache-dir \
+RUN python3 -m pip install --no-cache-dir --upgrade pip && \
+    python3 -m pip install --no-cache-dir \
     torch \
     torchvision \
     torchaudio \

docker/diffusers-pytorch-xformers-cuda/Dockerfile

@@ -23,13 +23,13 @@ RUN python3 -m venv /opt/venv
 ENV PATH="/opt/venv/bin:$PATH"
 
 # pre-install the heavy dependencies (these can later be overridden by the deps from setup.py)
-RUN python3 -m pip install --no-cache-dir --upgrade pip uv==0.1.11 && \
+RUN python3 -m pip install --no-cache-dir --upgrade pip && \
     python3 -m pip install --no-cache-dir \
         torch \
         torchvision \
         torchaudio \
         invisible_watermark && \
-    python3 -m uv pip install --no-cache-dir \
+    python3 -m pip install --no-cache-dir \
         accelerate \
         datasets \
         hf-doc-builder \

docs/source/en/_toctree.yml

@@ -18,18 +18,20 @@
   - local: tutorials/basic_training
     title: Train a diffusion model
   - local: tutorials/using_peft_for_inference
-    title: Load LoRAs for inference
+    title: Inference with PEFT
   - local: tutorials/fast_diffusion
     title: Accelerate inference of text-to-image diffusion models
   title: Tutorials
 - sections:
   - sections:
+    - local: using-diffusers/loading_overview
+      title: Overview
     - local: using-diffusers/loading
-      title: Load pipelines
+      title: Load pipelines, models, and schedulers
+    - local: using-diffusers/schedulers
+      title: Load and compare different schedulers
     - local: using-diffusers/custom_pipeline_overview
       title: Load community pipelines and components
-    - local: using-diffusers/schedulers
-      title: Load schedulers and models
     - local: using-diffusers/using_safetensors
       title: Load safetensors
     - local: using-diffusers/other-formats
@@ -60,8 +62,6 @@
       title: Textual inversion
     - local: using-diffusers/ip_adapter
       title: IP-Adapter
-    - local: using-diffusers/merge_loras
-      title: Merge LoRAs
     - local: training/distributed_inference
       title: Distributed inference with multiple GPUs
     - local: using-diffusers/reusing_seeds
@@ -69,7 +69,7 @@
     - local: using-diffusers/control_brightness
       title: Control image brightness
     - local: using-diffusers/weighted_prompts
-      title: Prompt techniques
+      title: Prompt weighting
     - local: using-diffusers/freeu
       title: Improve generation quality with FreeU
     title: Techniques
@@ -84,8 +84,6 @@
       title: Kandinsky
     - local: using-diffusers/controlnet
       title: ControlNet
-    - local: using-diffusers/t2i_adapter
-      title: T2I-Adapter
     - local: using-diffusers/shap-e
       title: Shap-E
     - local: using-diffusers/diffedit
@@ -104,8 +102,6 @@
       title: Latent Consistency Model-LoRA
     - local: using-diffusers/inference_with_lcm
       title: Latent Consistency Model
-    - local: using-diffusers/inference_with_tcd_lora
-      title: Trajectory Consistency Distillation-LoRA
     - local: using-diffusers/svd
       title: Stable Video Diffusion
     title: Specific pipeline examples
@@ -170,8 +166,6 @@
       title: Token merging
     - local: optimization/deepcache
       title: DeepCache
-    - local: optimization/tgate
-      title: TGATE
     title: General optimizations
   - sections:
     - local: using-diffusers/stable_diffusion_jax_how_to
@@ -282,10 +276,6 @@
       title: ControlNet
     - local: api/pipelines/controlnet_sdxl
       title: ControlNet with Stable Diffusion XL
-    - local: api/pipelines/controlnetxs
-      title: ControlNet-XS
-    - local: api/pipelines/controlnetxs_sdxl
-      title: ControlNet-XS with Stable Diffusion XL
     - local: api/pipelines/dance_diffusion
       title: Dance Diffusion
     - local: api/pipelines/ddim
@@ -312,8 +302,6 @@
       title: Latent Consistency Models
     - local: api/pipelines/latent_diffusion
       title: Latent Diffusion
-    - local: api/pipelines/ledits_pp
-      title: LEDITS++
     - local: api/pipelines/panorama
       title: MultiDiffusion
     - local: api/pipelines/musicldm
@@ -330,8 +318,6 @@
       title: Semantic Guidance
     - local: api/pipelines/shap_e
       title: Shap-E
-    - local: api/pipelines/stable_cascade
-      title: Stable Cascade
     - sections:
       - local: api/pipelines/stable_diffusion/overview
         title: Overview
@@ -364,7 +350,7 @@
       - local: api/pipelines/stable_diffusion/ldm3d_diffusion
         title: LDM3D Text-to-(RGB, Depth), Text-to-(RGB-pano, Depth-pano), LDM3D Upscaler
       - local: api/pipelines/stable_diffusion/adapter
-        title: T2I-Adapter
+        title: Stable Diffusion T2I-Adapter
       - local: api/pipelines/stable_diffusion/gligen
         title: GLIGEN (Grounded Language-to-Image Generation)
       title: Stable Diffusion
@@ -406,10 +392,6 @@
       title: DPMSolverSDEScheduler
     - local: api/schedulers/singlestep_dpm_solver
       title: DPMSolverSinglestepScheduler
-    - local: api/schedulers/edm_multistep_dpm_solver
-      title: EDMDPMSolverMultistepScheduler
-    - local: api/schedulers/edm_euler
-      title: EDMEulerScheduler
     - local: api/schedulers/euler_ancestral
       title: EulerAncestralDiscreteScheduler
     - local: api/schedulers/euler
@@ -436,8 +418,6 @@
       title: ScoreSdeVeScheduler
     - local: api/schedulers/score_sde_vp
       title: ScoreSdeVpScheduler
-    - local: api/schedulers/tcd
-      title: TCDScheduler
     - local: api/schedulers/unipc
       title: UniPCMultistepScheduler
     - local: api/schedulers/vq_diffusion

docs/source/en/api/attnprocessor.md

@@ -41,6 +41,12 @@ An attention processor is a class for applying different types of attention mech
 ## FusedAttnProcessor2_0
 [[autodoc]] models.attention_processor.FusedAttnProcessor2_0
 
+## LoRAAttnProcessor
+[[autodoc]] models.attention_processor.LoRAAttnProcessor
+
+## LoRAAttnProcessor2_0
+[[autodoc]] models.attention_processor.LoRAAttnProcessor2_0
+
 ## LoRAAttnAddedKVProcessor
 [[autodoc]] models.attention_processor.LoRAAttnAddedKVProcessor
 

docs/source/en/api/loaders/ip_adapter.md

@@ -23,7 +23,3 @@ Learn how to load an IP-Adapter checkpoint and image in the IP-Adapter [loading]
 ## IPAdapterMixin
 
 [[autodoc]] loaders.ip_adapter.IPAdapterMixin
-
-## IPAdapterMaskProcessor
-
-[[autodoc]] image_processor.IPAdapterMaskProcessor

docs/source/en/api/models/consistency_decoder_vae.md

@@ -1,18 +1,6 @@
-<!--Copyright 2024 The HuggingFace Team. All rights reserved.
-
-Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
-the License. You may obtain a copy of the License at
-
-http://www.apache.org/licenses/LICENSE-2.0
-
-Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
-an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
-specific language governing permissions and limitations under the License.
--->
-
 # Consistency Decoder
 
-Consistency decoder can be used to decode the latents from the denoising UNet in the [`StableDiffusionPipeline`]. This decoder was introduced in the [DALL-E 3 technical report](https://openai.com/dall-e-3).
+Consistency decoder can be used to decode the latents from the denoising UNet in the [`StableDiffusionPipeline`]. This decoder was introduced in the [DALL-E 3 technical report](https://openai.com/dall-e-3). 
 
 The original codebase can be found at [openai/consistencydecoder](https://github.com/openai/consistencydecoder).
 

docs/source/en/api/pipelines/animatediff.md

@@ -408,29 +408,6 @@ Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers)
 
 </Tip>
 
-<table>
-    <tr>
-      <th align=center>Without FreeInit enabled</th>
-      <th align=center>With FreeInit enabled</th>
-    </tr>
-    <tr>
-        <td align=center>
-          panda playing a guitar
-          <br />
-          <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/animatediff-no-freeinit.gif"
-              alt="panda playing a guitar"
-              style="width: 300px;" />
-        </td>
-        <td align=center>
-          panda playing a guitar
-          <br/>
-          <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/animatediff-freeinit.gif"
-              alt="panda playing a guitar"
-              style="width: 300px;" />
-        </td>
-    </tr>
-</table>
-
 ## Using AnimateLCM
 
 [AnimateLCM](https://animatelcm.github.io/) is a motion module checkpoint and an [LCM LoRA](https://huggingface.co/docs/diffusers/using-diffusers/inference_with_lcm_lora) that have been created using a consistency learning strategy that decouples the distillation of the image generation priors and the motion generation priors.
@@ -467,7 +444,7 @@ export_to_gif(frames, "animatelcm.gif")
         A space rocket, 4K.
         <br>
         <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/animatelcm-output.gif"
-            alt="A space rocket, 4K"
+            alt="masterpiece, bestquality, sunset"
             style="width: 300px;" />
         </center></td>
     </tr>
@@ -509,7 +486,7 @@ export_to_gif(frames, "animatelcm-motion-lora.gif")
         A space rocket, 4K.
         <br>
         <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/animatelcm-motion-lora.gif"
-            alt="A space rocket, 4K"
+            alt="masterpiece, bestquality, sunset"
             style="width: 300px;" />
         </center></td>
     </tr>

docs/source/en/api/pipelines/audioldm2.md

@@ -20,8 +20,7 @@ The abstract of the paper is the following:
 
 *Although audio generation shares commonalities across different types of audio, such as speech, music, and sound effects, designing models for each type requires careful consideration of specific objectives and biases that can significantly differ from those of other types. To bring us closer to a unified perspective of audio generation, this paper proposes a framework that utilizes the same learning method for speech, music, and sound effect generation. Our framework introduces a general representation of audio, called "language of audio" (LOA). Any audio can be translated into LOA based on AudioMAE, a self-supervised pre-trained representation learning model. In the generation process, we translate any modalities into LOA by using a GPT-2 model, and we perform self-supervised audio generation learning with a latent diffusion model conditioned on LOA. The proposed framework naturally brings advantages such as in-context learning abilities and reusable self-supervised pretrained AudioMAE and latent diffusion models. Experiments on the major benchmarks of text-to-audio, text-to-music, and text-to-speech demonstrate state-of-the-art or competitive performance against previous approaches. Our code, pretrained model, and demo are available at [this https URL](https://audioldm.github.io/audioldm2).*
 
-This pipeline was contributed by [sanchit-gandhi](https://huggingface.co/sanchit-gandhi) and [Nguyễn Công Tú Anh](https://github.com/tuanh123789). The original codebase can be 
-found at [haoheliu/audioldm2](https://github.com/haoheliu/audioldm2). 
+This pipeline was contributed by [sanchit-gandhi](https://huggingface.co/sanchit-gandhi). The original codebase can be found at [haoheliu/audioldm2](https://github.com/haoheliu/audioldm2).
 
 ## Tips
 
@@ -37,8 +36,6 @@ See table below for details on the three checkpoints:
 | [audioldm2](https://huggingface.co/cvssp/audioldm2)             | Text-to-audio | 350M            | 1.1B             | 1150k             |
 | [audioldm2-large](https://huggingface.co/cvssp/audioldm2-large) | Text-to-audio | 750M            | 1.5B             | 1150k             |
 | [audioldm2-music](https://huggingface.co/cvssp/audioldm2-music) | Text-to-music | 350M            | 1.1B             | 665k              |
-| [audioldm2-gigaspeech](https://huggingface.co/anhnct/audioldm2_gigaspeech) | Text-to-speech | 350M            | 1.1B             |10k              |
-| [audioldm2-ljspeech](https://huggingface.co/anhnct/audioldm2_ljspeech) | Text-to-speech | 350M            | 1.1B             |              |
 
 ### Constructing a prompt
 
@@ -56,7 +53,7 @@ See table below for details on the three checkpoints:
 * The quality of the generated waveforms can vary significantly based on the seed. Try generating with different seeds until you find a satisfactory generation.
 * Multiple waveforms can be generated in one go: set `num_waveforms_per_prompt` to a value greater than 1. Automatic scoring will be performed between the generated waveforms and prompt text, and the audios ranked from best to worst accordingly.
 
-The following example demonstrates how to construct good music and speech generation using the aforementioned tips: [example](https://huggingface.co/docs/diffusers/main/en/api/pipelines/audioldm2#diffusers.AudioLDM2Pipeline.__call__.example).
+The following example demonstrates how to construct good music generation using the aforementioned tips: [example](https://huggingface.co/docs/diffusers/main/en/api/pipelines/audioldm2#diffusers.AudioLDM2Pipeline.__call__.example).
 
 <Tip>
 

docs/source/en/api/pipelines/ledits_pp.md

@@ -1,54 +0,0 @@
-<!--Copyright 2023 The HuggingFace Team. All rights reserved.
-
-Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
-the License. You may obtain a copy of the License at
-
-http://www.apache.org/licenses/LICENSE-2.0
-
-Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
-an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
-specific language governing permissions and limitations under the License.
--->
-
-# LEDITS++
-
-LEDITS++ was proposed in [LEDITS++: Limitless Image Editing using Text-to-Image Models](https://huggingface.co/papers/2311.16711) by Manuel Brack, Felix Friedrich, Katharina Kornmeier, Linoy Tsaban, Patrick Schramowski, Kristian Kersting, Apolinário Passos.
-
-The abstract from the paper is:
-
-*Text-to-image diffusion models have recently received increasing interest for their astonishing ability to produce high-fidelity images from solely text inputs. Subsequent research efforts aim to exploit and apply their capabilities to real image editing. However, existing image-to-image methods are often inefficient, imprecise, and of limited versatility. They either require time-consuming fine-tuning, deviate unnecessarily strongly from the input image, and/or lack support for multiple, simultaneous edits. To address these issues, we introduce LEDITS++, an efficient yet versatile and precise textual image manipulation technique. LEDITS++'s novel inversion approach requires no tuning nor optimization and produces high-fidelity results with a few diffusion steps. Second, our methodology supports multiple simultaneous edits and is architecture-agnostic. Third, we use a novel implicit masking technique that limits changes to relevant image regions. We propose the novel TEdBench++ benchmark as part of our exhaustive evaluation. Our results demonstrate the capabilities of LEDITS++ and its improvements over previous methods. The project page is available at https://leditsplusplus-project.static.hf.space .*
-
-<Tip>
-
-You can find additional information about LEDITS++ on the [project page](https://leditsplusplus-project.static.hf.space/index.html) and try it out in a [demo](https://huggingface.co/spaces/editing-images/leditsplusplus).
-
-</Tip>
-
-<Tip warning={true}>
-Due to some backward compatability issues with the current diffusers implementation of [`~schedulers.DPMSolverMultistepScheduler`] this implementation of LEdits++ can no longer guarantee perfect inversion. 
-This issue is unlikely to have any noticeable effects on applied use-cases. However, we provide an alternative implementation that guarantees perfect inversion in a dedicated [GitHub repo](https://github.com/ml-research/ledits_pp). 
-</Tip>
-
-We provide two distinct pipelines based on different pre-trained models. 
-
-## LEditsPPPipelineStableDiffusion
-[[autodoc]] pipelines.ledits_pp.LEditsPPPipelineStableDiffusion
-	- all
-	- __call__
-	- invert
-
-## LEditsPPPipelineStableDiffusionXL
-[[autodoc]] pipelines.ledits_pp.LEditsPPPipelineStableDiffusionXL
-	- all
-	- __call__
-	- invert
-
-
-
-## LEditsPPDiffusionPipelineOutput
-[[autodoc]] pipelines.ledits_pp.pipeline_output.LEditsPPDiffusionPipelineOutput
-	- all
-
-## LEditsPPInversionPipelineOutput
-[[autodoc]] pipelines.ledits_pp.pipeline_output.LEditsPPInversionPipelineOutput
-	- all

docs/source/en/api/pipelines/overview.md

@@ -57,7 +57,6 @@ The table below lists all the pipelines currently available in 🤗 Diffusers an
 | [Latent Consistency Models](latent_consistency_models) | text2image |
 | [Latent Diffusion](latent_diffusion) | text2image, super-resolution |
 | [LDM3D](stable_diffusion/ldm3d_diffusion) | text2image, text-to-3D, text-to-pano, upscaling |
-| [LEDITS++](ledits_pp) | image editing |
 | [MultiDiffusion](panorama) | text2image |
 | [MusicLDM](musicldm) | text2audio |
 | [Paint by Example](paint_by_example) | inpainting |

docs/source/en/api/pipelines/semantic_stable_diffusion.md

@@ -30,6 +30,6 @@ Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers)
 	- all
 	- __call__
 
-## SemanticStableDiffusionPipelineOutput
+## StableDiffusionSafePipelineOutput
 [[autodoc]] pipelines.semantic_stable_diffusion.pipeline_output.SemanticStableDiffusionPipelineOutput
 	- all

docs/source/en/api/pipelines/stable_cascade.md

@@ -1,229 +0,0 @@
-<!--Copyright 2024 The HuggingFace Team. All rights reserved.
-
-Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
-the License. You may obtain a copy of the License at
-
-http://www.apache.org/licenses/LICENSE-2.0
-
-Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
-an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
-specific language governing permissions and limitations under the License.
--->
-
-# Stable Cascade
-
-This model is built upon the [Würstchen](https://openreview.net/forum?id=gU58d5QeGv) architecture and its main
-difference to other models like Stable Diffusion is that it is working at a much smaller latent space. Why is this
-important? The smaller the latent space, the **faster** you can run inference and the **cheaper** the training becomes.
-How small is the latent space? Stable Diffusion uses a compression factor of 8, resulting in a 1024x1024 image being
-encoded to 128x128. Stable Cascade achieves a compression factor of 42, meaning that it is possible to encode a
-1024x1024 image to 24x24, while maintaining crisp reconstructions. The text-conditional model is then trained in the
-highly compressed latent space. Previous versions of this architecture, achieved a 16x cost reduction over Stable
-Diffusion 1.5.
-
-Therefore, this kind of model is well suited for usages where efficiency is important. Furthermore, all known extensions
-like finetuning, LoRA, ControlNet, IP-Adapter, LCM etc. are possible with this method as well.
-
-The original codebase can be found at [Stability-AI/StableCascade](https://github.com/Stability-AI/StableCascade).
-
-## Model Overview
-Stable Cascade consists of three models: Stage A, Stage B and Stage C, representing a cascade to generate images,
-hence the name "Stable Cascade".
-
-Stage A & B are used to compress images, similar to what the job of the VAE is in Stable Diffusion.
-However, with this setup, a much higher compression of images can be achieved. While the Stable Diffusion models use a
-spatial compression factor of 8, encoding an image with resolution of 1024 x 1024 to 128 x 128, Stable Cascade achieves
-a compression factor of 42. This encodes a 1024 x 1024 image to 24 x 24, while being able to accurately decode the
-image. This comes with the great benefit of cheaper training and inference. Furthermore, Stage C is responsible
-for generating the small 24 x 24 latents given a text prompt.
-
-The Stage C model operates on the small 24 x 24 latents and denoises the latents conditioned on text prompts. The model is also the largest component in the Cascade pipeline and is meant to be used with the `StableCascadePriorPipeline`
-
-The Stage B and Stage A models are used with the `StableCascadeDecoderPipeline` and are responsible for generating the final image given the small 24 x 24 latents.
-
-<Tip warning={true}>
-
-There are some restrictions on data types that can be used with the Stable Cascade models. The official checkpoints for the  `StableCascadePriorPipeline` do not support the `torch.float16` data type. Please use `torch.bfloat16` instead.
-
-In order to use the `torch.bfloat16` data type with the `StableCascadeDecoderPipeline` you need to have PyTorch 2.2.0 or higher installed. This also means that using the `StableCascadeCombinedPipeline` with `torch.bfloat16` requires PyTorch 2.2.0 or higher, since it calls the `StableCascadeDecoderPipeline` internally.
-
-If it is not possible to install PyTorch 2.2.0 or higher in your environment, the `StableCascadeDecoderPipeline` can be used on its own with the `torch.float16` data type. You can download the full precision or `bf16` variant weights for the pipeline and cast the weights to `torch.float16`.
-
-</Tip>
-
-## Usage example
-
-```python
-import torch
-from diffusers import StableCascadeDecoderPipeline, StableCascadePriorPipeline
-
-prompt = "an image of a shiba inu, donning a spacesuit and helmet"
-negative_prompt = ""
-
-prior = StableCascadePriorPipeline.from_pretrained("stabilityai/stable-cascade-prior", variant="bf16", torch_dtype=torch.bfloat16)
-decoder = StableCascadeDecoderPipeline.from_pretrained("stabilityai/stable-cascade", variant="bf16", torch_dtype=torch.float16)
-
-prior.enable_model_cpu_offload()
-prior_output = prior(
-    prompt=prompt,
-    height=1024,
-    width=1024,
-    negative_prompt=negative_prompt,
-    guidance_scale=4.0,
-    num_images_per_prompt=1,
-    num_inference_steps=20
-)
-
-decoder.enable_model_cpu_offload()
-decoder_output = decoder(
-    image_embeddings=prior_output.image_embeddings.to(torch.float16),
-    prompt=prompt,
-    negative_prompt=negative_prompt,
-    guidance_scale=0.0,
-    output_type="pil",
-    num_inference_steps=10
-).images[0]
-decoder_output.save("cascade.png")
-```
-
-## Using the Lite Versions of the Stage B and Stage C models
-
-```python
-import torch
-from diffusers import (
-    StableCascadeDecoderPipeline,
-    StableCascadePriorPipeline,
-    StableCascadeUNet,
-)
-
-prompt = "an image of a shiba inu, donning a spacesuit and helmet"
-negative_prompt = ""
-
-prior_unet = StableCascadeUNet.from_pretrained("stabilityai/stable-cascade-prior", subfolder="prior_lite")
-decoder_unet = StableCascadeUNet.from_pretrained("stabilityai/stable-cascade", subfolder="decoder_lite")
-
-prior = StableCascadePriorPipeline.from_pretrained("stabilityai/stable-cascade-prior", prior=prior_unet)
-decoder = StableCascadeDecoderPipeline.from_pretrained("stabilityai/stable-cascade", decoder=decoder_unet)
-
-prior.enable_model_cpu_offload()
-prior_output = prior(
-    prompt=prompt,
-    height=1024,
-    width=1024,
-    negative_prompt=negative_prompt,
-    guidance_scale=4.0,
-    num_images_per_prompt=1,
-    num_inference_steps=20
-)
-
-decoder.enable_model_cpu_offload()
-decoder_output = decoder(
-    image_embeddings=prior_output.image_embeddings,
-    prompt=prompt,
-    negative_prompt=negative_prompt,
-    guidance_scale=0.0,
-    output_type="pil",
-    num_inference_steps=10
-).images[0]
-decoder_output.save("cascade.png")
-```
-
-## Loading original checkpoints with `from_single_file`
-
-Loading the original format checkpoints is supported via `from_single_file` method in the StableCascadeUNet.
-
-```python
-import torch
-from diffusers import (
-    StableCascadeDecoderPipeline,
-    StableCascadePriorPipeline,
-    StableCascadeUNet,
-)
-
-prompt = "an image of a shiba inu, donning a spacesuit and helmet"
-negative_prompt = ""
-
-prior_unet = StableCascadeUNet.from_single_file(
-    "https://huggingface.co/stabilityai/stable-cascade/resolve/main/stage_c_bf16.safetensors",
-    torch_dtype=torch.bfloat16
-)
-decoder_unet = StableCascadeUNet.from_single_file(
-    "https://huggingface.co/stabilityai/stable-cascade/blob/main/stage_b_bf16.safetensors",
-    torch_dtype=torch.bfloat16
-)
-
-prior = StableCascadePriorPipeline.from_pretrained("stabilityai/stable-cascade-prior", prior=prior_unet, torch_dtype=torch.bfloat16)
-decoder = StableCascadeDecoderPipeline.from_pretrained("stabilityai/stable-cascade", decoder=decoder_unet, torch_dtype=torch.bfloat16)
-
-prior.enable_model_cpu_offload()
-prior_output = prior(
-    prompt=prompt,
-    height=1024,
-    width=1024,
-    negative_prompt=negative_prompt,
-    guidance_scale=4.0,
-    num_images_per_prompt=1,
-    num_inference_steps=20
-)
-
-decoder.enable_model_cpu_offload()
-decoder_output = decoder(
-    image_embeddings=prior_output.image_embeddings,
-    prompt=prompt,
-    negative_prompt=negative_prompt,
-    guidance_scale=0.0,
-    output_type="pil",
-    num_inference_steps=10
-).images[0]
-decoder_output.save("cascade-single-file.png")
-```
-
-## Uses
-
-### Direct Use
-
-The model is intended for research purposes for now. Possible research areas and tasks include
-
-- Research on generative models.
-- Safe deployment of models which have the potential to generate harmful content.
-- Probing and understanding the limitations and biases of generative models.
-- Generation of artworks and use in design and other artistic processes.
-- Applications in educational or creative tools.
-
-Excluded uses are described below.
-
-### Out-of-Scope Use
-
-The model was not trained to be factual or true representations of people or events,
-and therefore using the model to generate such content is out-of-scope for the abilities of this model.
-The model should not be used in any way that violates Stability AI's [Acceptable Use Policy](https://stability.ai/use-policy).
-
-## Limitations and Bias
-
-### Limitations
-- Faces and people in general may not be generated properly.
-- The autoencoding part of the model is lossy.
-
-
-## StableCascadeCombinedPipeline
-
-[[autodoc]] StableCascadeCombinedPipeline
-	- all
-	- __call__
-
-## StableCascadePriorPipeline
-
-[[autodoc]] StableCascadePriorPipeline
-	- all
-	- __call__
-
-## StableCascadePriorPipelineOutput
-
-[[autodoc]] pipelines.stable_cascade.pipeline_stable_cascade_prior.StableCascadePriorPipelineOutput
-
-## StableCascadeDecoderPipeline
-
-[[autodoc]] StableCascadeDecoderPipeline
-	- all
-	- __call__
-

docs/source/en/api/pipelines/stable_diffusion/adapter.md

@@ -10,7 +10,9 @@ an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express o
 specific language governing permissions and limitations under the License.
 -->
 
-# T2I-Adapter
+# Text-to-Image Generation with Adapter Conditioning
+
+## Overview
 
 [T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models](https://arxiv.org/abs/2302.08453) by Chong Mou, Xintao Wang, Liangbin Xie, Jian Zhang, Zhongang Qi, Ying Shan, Xiaohu Qie.
 
@@ -22,26 +24,236 @@ The abstract of the paper is the following:
 
 This model was contributed by the community contributor [HimariO](https://github.com/HimariO) ❤️ .
 
-## StableDiffusionAdapterPipeline
+## Available Pipelines:
 
+| Pipeline | Tasks | Demo
+|---|---|:---:|
+| [StableDiffusionAdapterPipeline](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/t2i_adapter/pipeline_stable_diffusion_adapter.py) | *Text-to-Image Generation with T2I-Adapter Conditioning* | -
+| [StableDiffusionXLAdapterPipeline](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/t2i_adapter/pipeline_stable_diffusion_xl_adapter.py) | *Text-to-Image Generation with T2I-Adapter Conditioning on StableDiffusion-XL* | -
+
+## Usage example with the base model of StableDiffusion-1.4/1.5
+
+In the following we give a simple example of how to use a *T2I-Adapter* checkpoint with Diffusers for inference based on StableDiffusion-1.4/1.5.
+All adapters use the same pipeline.
+
+ 1. Images are first converted into the appropriate *control image* format.
+ 2. The *control image* and *prompt* are passed to the [`StableDiffusionAdapterPipeline`].
+
+Let's have a look at a simple example using the [Color Adapter](https://huggingface.co/TencentARC/t2iadapter_color_sd14v1).
+
+```python
+from diffusers.utils import load_image, make_image_grid
+
+image = load_image("https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/color_ref.png")
+```
+
+![img](https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/color_ref.png)
+
+
+Then we can create our color palette by simply resizing it to 8 by 8 pixels and then scaling it back to original size.
+
+```python
+from PIL import Image
+
+color_palette = image.resize((8, 8))
+color_palette = color_palette.resize((512, 512), resample=Image.Resampling.NEAREST)
+```
+
+Let's take a look at the processed image.
+
+![img](https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/color_palette.png)
+
+
+Next, create the adapter pipeline
+
+```py
+import torch
+from diffusers import StableDiffusionAdapterPipeline, T2IAdapter
+
+adapter = T2IAdapter.from_pretrained("TencentARC/t2iadapter_color_sd14v1", torch_dtype=torch.float16)
+pipe = StableDiffusionAdapterPipeline.from_pretrained(
+    "CompVis/stable-diffusion-v1-4",
+    adapter=adapter,
+    torch_dtype=torch.float16,
+)
+pipe.to("cuda")
+```
+
+Finally, pass the prompt and control image to the pipeline
+
+```py
+# fix the random seed, so you will get the same result as the example
+generator = torch.Generator("cuda").manual_seed(7)
+
+out_image = pipe(
+    "At night, glowing cubes in front of the beach",
+    image=color_palette,
+    generator=generator,
+).images[0]
+make_image_grid([image, color_palette, out_image], rows=1, cols=3)
+```
+
+![img](https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/color_output.png)
+
+## Usage example with the base model of StableDiffusion-XL
+
+In the following we give a simple example of how to use a *T2I-Adapter* checkpoint with Diffusers for inference based on StableDiffusion-XL.
+All adapters use the same pipeline.
+
+ 1. Images are first downloaded into the appropriate *control image* format.
+ 2. The *control image* and *prompt* are passed to the [`StableDiffusionXLAdapterPipeline`].
+
+Let's have a look at a simple example using the [Sketch Adapter](https://huggingface.co/Adapter/t2iadapter/tree/main/sketch_sdxl_1.0).
+
+```python
+from diffusers.utils import load_image, make_image_grid
+
+sketch_image = load_image("https://huggingface.co/Adapter/t2iadapter/resolve/main/sketch.png").convert("L")
+```
+
+![img](https://huggingface.co/Adapter/t2iadapter/resolve/main/sketch.png)
+
+Then, create the adapter pipeline
+
+```py
+import torch
+from diffusers import (
+    T2IAdapter,
+    StableDiffusionXLAdapterPipeline,
+    DDPMScheduler
+)
+
+model_id = "stabilityai/stable-diffusion-xl-base-1.0"
+adapter = T2IAdapter.from_pretrained("Adapter/t2iadapter", subfolder="sketch_sdxl_1.0", torch_dtype=torch.float16, adapter_type="full_adapter_xl")
+scheduler = DDPMScheduler.from_pretrained(model_id, subfolder="scheduler")
+
+pipe = StableDiffusionXLAdapterPipeline.from_pretrained(
+    model_id, adapter=adapter, safety_checker=None, torch_dtype=torch.float16, variant="fp16", scheduler=scheduler
+)
+
+pipe.to("cuda")
+```
+
+Finally, pass the prompt and control image to the pipeline
+
+```py
+# fix the random seed, so you will get the same result as the example
+generator = torch.Generator().manual_seed(42)
+
+sketch_image_out = pipe(
+    prompt="a photo of a dog in real world, high quality",
+    negative_prompt="extra digit, fewer digits, cropped, worst quality, low quality",
+    image=sketch_image,
+    generator=generator,
+    guidance_scale=7.5
+).images[0]
+make_image_grid([sketch_image, sketch_image_out], rows=1, cols=2)
+```
+
+![img](https://huggingface.co/Adapter/t2iadapter/resolve/main/sketch_output.png)
+
+## Available checkpoints
+
+Non-diffusers checkpoints can be found under [TencentARC/T2I-Adapter](https://huggingface.co/TencentARC/T2I-Adapter/tree/main/models).
+
+### T2I-Adapter with Stable Diffusion 1.4
+
+| Model Name | Control Image Overview| Control Image Example | Generated Image Example |
+|---|---|---|---|
+|[TencentARC/t2iadapter_color_sd14v1](https://huggingface.co/TencentARC/t2iadapter_color_sd14v1)<br/> *Trained with spatial color palette* | An image with 8x8 color palette.|<a href="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/color_sample_input.png"><img width="64" style="margin:0;padding:0;" src="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/color_sample_input.png"/></a>|<a href="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/color_sample_output.png"><img width="64" src="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/color_sample_output.png"/></a>|
+|[TencentARC/t2iadapter_canny_sd14v1](https://huggingface.co/TencentARC/t2iadapter_canny_sd14v1)<br/> *Trained with canny edge detection* | A monochrome image with white edges on a black background.|<a href="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/canny_sample_input.png"><img width="64" style="margin:0;padding:0;" src="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/canny_sample_input.png"/></a>|<a href="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/canny_sample_output.png"><img width="64" src="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/canny_sample_output.png"/></a>|
+|[TencentARC/t2iadapter_sketch_sd14v1](https://huggingface.co/TencentARC/t2iadapter_sketch_sd14v1)<br/> *Trained with [PidiNet](https://github.com/zhuoinoulu/pidinet) edge detection* | A hand-drawn monochrome image with white outlines on a black background.|<a href="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/sketch_sample_input.png"><img width="64" style="margin:0;padding:0;" src="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/sketch_sample_input.png"/></a>|<a href="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/sketch_sample_output.png"><img width="64" src="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/sketch_sample_output.png"/></a>|
+|[TencentARC/t2iadapter_depth_sd14v1](https://huggingface.co/TencentARC/t2iadapter_depth_sd14v1)<br/> *Trained with Midas depth estimation*  | A grayscale image with black representing deep areas and white representing shallow areas.|<a href="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/depth_sample_input.png"><img width="64" src="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/depth_sample_input.png"/></a>|<a href="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/depth_sample_output.png"><img width="64" src="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/depth_sample_output.png"/></a>|
+|[TencentARC/t2iadapter_openpose_sd14v1](https://huggingface.co/TencentARC/t2iadapter_openpose_sd14v1)<br/> *Trained with OpenPose bone image*  | A [OpenPose bone](https://github.com/CMU-Perceptual-Computing-Lab/openpose) image.|<a href="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/openpose_sample_input.png"><img width="64" src="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/openpose_sample_input.png"/></a>|<a href="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/openpose_sample_output.png"><img width="64" src="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/openpose_sample_output.png"/></a>|
+|[TencentARC/t2iadapter_keypose_sd14v1](https://huggingface.co/TencentARC/t2iadapter_keypose_sd14v1)<br/> *Trained with mmpose skeleton image*  | A [mmpose skeleton](https://github.com/open-mmlab/mmpose) image.|<a href="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/keypose_sample_input.png"><img width="64" src="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/keypose_sample_input.png"/></a>|<a href="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/keypose_sample_output.png"><img width="64" src="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/keypose_sample_output.png"/></a>|
+|[TencentARC/t2iadapter_seg_sd14v1](https://huggingface.co/TencentARC/t2iadapter_seg_sd14v1)<br/>*Trained with semantic segmentation*  | An [custom](https://github.com/TencentARC/T2I-Adapter/discussions/25) segmentation protocol image.|<a href="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/seg_sample_input.png"><img width="64" src="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/seg_sample_input.png"/></a>|<a href="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/seg_sample_output.png"><img width="64" src="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/seg_sample_output.png"/></a> |
+|[TencentARC/t2iadapter_canny_sd15v2](https://huggingface.co/TencentARC/t2iadapter_canny_sd15v2)||
+|[TencentARC/t2iadapter_depth_sd15v2](https://huggingface.co/TencentARC/t2iadapter_depth_sd15v2)||
+|[TencentARC/t2iadapter_sketch_sd15v2](https://huggingface.co/TencentARC/t2iadapter_sketch_sd15v2)||
+|[TencentARC/t2iadapter_zoedepth_sd15v1](https://huggingface.co/TencentARC/t2iadapter_zoedepth_sd15v1)||
+|[Adapter/t2iadapter, subfolder='sketch_sdxl_1.0'](https://huggingface.co/Adapter/t2iadapter/tree/main/sketch_sdxl_1.0)||
+|[Adapter/t2iadapter, subfolder='canny_sdxl_1.0'](https://huggingface.co/Adapter/t2iadapter/tree/main/canny_sdxl_1.0)||
+|[Adapter/t2iadapter, subfolder='openpose_sdxl_1.0'](https://huggingface.co/Adapter/t2iadapter/tree/main/openpose_sdxl_1.0)||
+
+## Combining multiple adapters
+
+[`MultiAdapter`] can be used for applying multiple conditionings at once.
+
+Here we use the keypose adapter for the character posture and the depth adapter for creating the scene.
+
+```py
+from diffusers.utils import load_image, make_image_grid
+
+cond_keypose = load_image(
+    "https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/keypose_sample_input.png"
+)
+cond_depth = load_image(
+    "https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/depth_sample_input.png"
+)
+cond = [cond_keypose, cond_depth]
+
+prompt = ["A man walking in an office room with a nice view"]
+```
+
+The two control images look as such:
+
+![img](https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/keypose_sample_input.png)
+![img](https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/depth_sample_input.png)
+
+
+`MultiAdapter` combines keypose and depth adapters.
+
+`adapter_conditioning_scale` balances the relative influence of the different adapters.
+
+```py
+import torch
+from diffusers import StableDiffusionAdapterPipeline, MultiAdapter, T2IAdapter
+
+adapters = MultiAdapter(
+    [
+        T2IAdapter.from_pretrained("TencentARC/t2iadapter_keypose_sd14v1"),
+        T2IAdapter.from_pretrained("TencentARC/t2iadapter_depth_sd14v1"),
+    ]
+)
+adapters = adapters.to(torch.float16)
+
+pipe = StableDiffusionAdapterPipeline.from_pretrained(
+    "CompVis/stable-diffusion-v1-4",
+    torch_dtype=torch.float16,
+    adapter=adapters,
+).to("cuda")
+
+image = pipe(prompt, cond, adapter_conditioning_scale=[0.8, 0.8]).images[0]
+make_image_grid([cond_keypose, cond_depth, image], rows=1, cols=3)
+```
+
+![img](https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/keypose_depth_sample_output.png)
+
+
+## T2I-Adapter vs ControlNet
+
+T2I-Adapter is similar to [ControlNet](https://huggingface.co/docs/diffusers/main/en/api/pipelines/controlnet).
+T2I-Adapter uses a smaller auxiliary network which is only run once for the entire diffusion process.
+However, T2I-Adapter performs slightly worse than ControlNet.
+
+## StableDiffusionAdapterPipeline
 [[autodoc]] StableDiffusionAdapterPipeline
-    - all
-    - __call__
-    - enable_attention_slicing
-    - disable_attention_slicing
-    - enable_vae_slicing
-    - disable_vae_slicing
-    - enable_xformers_memory_efficient_attention
-    - disable_xformers_memory_efficient_attention
+	- all
+	- __call__
+	- enable_attention_slicing
+	- disable_attention_slicing
+	- enable_vae_slicing
+	- disable_vae_slicing
+	- enable_xformers_memory_efficient_attention
+	- disable_xformers_memory_efficient_attention
 
 ## StableDiffusionXLAdapterPipeline
-
 [[autodoc]] StableDiffusionXLAdapterPipeline
-    - all
-    - __call__
-    - enable_attention_slicing
-    - disable_attention_slicing
-    - enable_vae_slicing
-    - disable_vae_slicing
-    - enable_xformers_memory_efficient_attention
-    - disable_xformers_memory_efficient_attention
+	- all
+	- __call__
+	- enable_attention_slicing
+	- disable_attention_slicing
+	- enable_vae_slicing
+	- disable_vae_slicing
+	- enable_xformers_memory_efficient_attention
+	- disable_xformers_memory_efficient_attention

docs/source/en/api/pipelines/stable_diffusion/overview.md

@@ -172,41 +172,3 @@ inpaint = StableDiffusionInpaintPipeline(**text2img.components)
 
 # now you can use text2img(...), img2img(...), inpaint(...) just like the call methods of each respective pipeline
 ```
-
-### Create web demos using `gradio`
-
-The Stable Diffusion pipelines are automatically supported in [Gradio](https://github.com/gradio-app/gradio/), a library that makes creating beautiful and user-friendly machine learning apps on the web a breeze. First, make sure you have Gradio installed:
-
-```
-pip install -U gradio
-```
-
-Then, create a web demo around any Stable Diffusion-based pipeline. For example, you can create an image generation pipeline in a single line of code with Gradio's [`Interface.from_pipeline`](https://www.gradio.app/docs/interface#interface-from-pipeline) function:
-
-```py
-from diffusers import StableDiffusionPipeline
-import gradio as gr
-
-pipe = StableDiffusionPipeline.from_pretrained("CompVis/stable-diffusion-v1-4")
-
-gr.Interface.from_pipeline(pipe).launch()
-```
-
-which opens an intuitive drag-and-drop interface in your browser:
-
-![](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/gradio-panda.png)
-
-Similarly, you could create a demo for an image-to-image pipeline with:
-
-```py
-from diffusers import StableDiffusionImg2ImgPipeline
-import gradio as gr
-
-
-pipe = StableDiffusionImg2ImgPipeline.from_pretrained("runwayml/stable-diffusion-v1-5")
-
-gr.Interface.from_pipeline(pipe).launch()
-```
-
-By default, the web demo runs on a local server. If you'd like to share it with others, you can generate a temporary public
-link by setting `share=True` in `launch()`. Or, you can host your demo on [Hugging Face Spaces](https://huggingface.co/spaces)https://huggingface.co/spaces for a permanent link. 

docs/source/en/api/pipelines/stable_diffusion/sdxl_turbo.md

@@ -21,7 +21,7 @@ The abstract from the paper is:
 ## Tips
 
 - SDXL Turbo uses the exact same architecture as [SDXL](./stable_diffusion_xl), which means it also has the same API. Please refer to the [SDXL](./stable_diffusion_xl) API reference for more details.
-- SDXL Turbo should disable guidance scale by setting `guidance_scale=0.0`.
+- SDXL Turbo should disable guidance scale by setting `guidance_scale=0.0`
 - SDXL Turbo should use `timestep_spacing='trailing'` for the scheduler and use between 1 and 4 steps.
 - SDXL Turbo has been trained to generate images of size 512x512.
 - SDXL Turbo is open-access, but not open-source meaning that one might have to buy a model license in order to use it for commercial applications. Make sure to read the [official model card](https://huggingface.co/stabilityai/sdxl-turbo) to learn more.

docs/source/en/api/schedulers/consistency_decoder.md

@@ -1,21 +1,9 @@
-<!--Copyright 2024 The HuggingFace Team. All rights reserved.
-
-Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
-the License. You may obtain a copy of the License at
-
-http://www.apache.org/licenses/LICENSE-2.0
-
-Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
-an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
-specific language governing permissions and limitations under the License.
--->
-
 # ConsistencyDecoderScheduler
 
-This scheduler is a part of the [`ConsistencyDecoderPipeline`] and was introduced in [DALL-E 3](https://openai.com/dall-e-3).
+This scheduler is a part of the [`ConsistencyDecoderPipeline`] and was introduced in [DALL-E 3](https://openai.com/dall-e-3). 
 
 The original codebase can be found at [openai/consistency_models](https://github.com/openai/consistency_models).
 
 
 ## ConsistencyDecoderScheduler
-[[autodoc]] schedulers.scheduling_consistency_decoder.ConsistencyDecoderScheduler
+[[autodoc]] schedulers.scheduling_consistency_decoder.ConsistencyDecoderScheduler

docs/source/en/api/schedulers/edm_euler.md

@@ -1,22 +0,0 @@
-<!--Copyright 2024 The HuggingFace Team. All rights reserved.
-
-Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
-the License. You may obtain a copy of the License at
-
-http://www.apache.org/licenses/LICENSE-2.0
-
-Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
-an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
-specific language governing permissions and limitations under the License.
--->
-
-# EDMEulerScheduler
-
-The Karras formulation of the Euler scheduler (Algorithm 2) from the [Elucidating the Design Space of Diffusion-Based Generative Models](https://huggingface.co/papers/2206.00364) paper by Karras et al. This is a fast scheduler which can often generate good outputs in 20-30 steps. The scheduler is based on the original [k-diffusion](https://github.com/crowsonkb/k-diffusion/blob/481677d114f6ea445aa009cf5bd7a9cdee909e47/k_diffusion/sampling.py#L51) implementation by [Katherine Crowson](https://github.com/crowsonkb/).
-
-
-## EDMEulerScheduler
-[[autodoc]] EDMEulerScheduler
-
-## EDMEulerSchedulerOutput
-[[autodoc]] schedulers.scheduling_edm_euler.EDMEulerSchedulerOutput

docs/source/en/api/schedulers/edm_multistep_dpm_solver.md

@@ -1,24 +0,0 @@
-<!--Copyright 2024 The HuggingFace Team. All rights reserved.
-
-Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
-the License. You may obtain a copy of the License at
-
-http://www.apache.org/licenses/LICENSE-2.0
-
-Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
-an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
-specific language governing permissions and limitations under the License.
--->
-
-# EDMDPMSolverMultistepScheduler
-
-`EDMDPMSolverMultistepScheduler` is a [Karras formulation](https://huggingface.co/papers/2206.00364) of `DPMSolverMultistep`, a multistep scheduler from [DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps](https://huggingface.co/papers/2206.00927) and [DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models](https://huggingface.co/papers/2211.01095) by Cheng Lu, Yuhao Zhou, Fan Bao, Jianfei Chen, Chongxuan Li, and Jun Zhu.
-
-DPMSolver (and the improved version DPMSolver++) is a fast dedicated high-order solver for diffusion ODEs with convergence order guarantee. Empirically, DPMSolver sampling with only 20 steps can generate high-quality
-samples, and it can generate quite good samples even in 10 steps.
-
-## EDMDPMSolverMultistepScheduler
-[[autodoc]] EDMDPMSolverMultistepScheduler
-
-## SchedulerOutput
-[[autodoc]] schedulers.scheduling_utils.SchedulerOutput

docs/source/en/api/schedulers/tcd.md

@@ -1,29 +0,0 @@
-<!--Copyright 2024 The HuggingFace Team. All rights reserved.
-
-Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
-the License. You may obtain a copy of the License at
-
-http://www.apache.org/licenses/LICENSE-2.0
-
-Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
-an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
-specific language governing permissions and limitations under the License.
--->
-
-# TCDScheduler 
-
-[Trajectory Consistency Distillation](https://huggingface.co/papers/2402.19159) by Jianbin Zheng, Minghui Hu, Zhongyi Fan, Chaoyue Wang, Changxing Ding, Dacheng Tao and Tat-Jen Cham introduced a Strategic Stochastic Sampling (Algorithm 4) that is capable of generating good samples in a small number of steps. Distinguishing it as an advanced iteration of the multistep scheduler (Algorithm 1) in the [Consistency Models](https://huggingface.co/papers/2303.01469), Strategic Stochastic Sampling specifically tailored for the trajectory consistency function.
-
-The abstract from the paper is:
-
-*Latent Consistency Model (LCM) extends the Consistency Model to the latent space and leverages the guided consistency distillation technique to achieve impressive performance in accelerating text-to-image synthesis. However, we observed that LCM struggles to generate images with both clarity and detailed intricacy. To address this limitation, we initially delve into and elucidate the underlying causes. Our investigation identifies that the primary issue stems from errors in three distinct areas. Consequently, we introduce Trajectory Consistency Distillation (TCD), which encompasses trajectory consistency function and strategic stochastic sampling. The trajectory consistency function diminishes the distillation errors by broadening the scope of the self-consistency boundary condition and endowing the TCD with the ability to accurately trace the entire trajectory of the Probability Flow ODE. Additionally, strategic stochastic sampling is specifically designed to circumvent the accumulated errors inherent in multi-step consistency sampling, which is meticulously tailored to complement the TCD model. Experiments demonstrate that TCD not only significantly enhances image quality at low NFEs but also yields more detailed results compared to the teacher model at high NFEs.*
-
-The original codebase can be found at [jabir-zheng/TCD](https://github.com/jabir-zheng/TCD).
-
-## TCDScheduler
-[[autodoc]] TCDScheduler
-
-
-## TCDSchedulerOutput
-[[autodoc]] schedulers.scheduling_tcd.TCDSchedulerOutput
-

docs/source/en/optimization/fp16.md

@@ -66,9 +66,3 @@ image = pipe(prompt).images[0]
 Don't use [`torch.autocast`](https://pytorch.org/docs/stable/amp.html#torch.autocast) in any of the pipelines as it can lead to black images and is always slower than pure float16 precision.
 
 </Tip>
-
-## Distilled model
-
-You could also use a distilled Stable Diffusion model and autoencoder to speed up inference. During distillation, many of the UNet's residual and attention blocks are shed to reduce the model size. The distilled model is faster and uses less memory while generating images of comparable quality to the full Stable Diffusion model.
-
-Learn more about in the [Distilled Stable Diffusion inference](../using-diffusers/distilled_sd) guide!

docs/source/en/optimization/tgate.md

@@ -1,182 +0,0 @@
-# T-GATE
-
-[T-GATE](https://github.com/HaozheLiu-ST/T-GATE/tree/main) accelerates inference for [Stable Diffusion](../api/pipelines/stable_diffusion/overview), [PixArt](../api/pipelines/pixart), and [Latency Consistency Model](../api/pipelines/latent_consistency_models.md) pipelines by skipping the cross-attention calculation once it converges. This method doesn't require any additional training and it can speed up inference from 10-50%. T-GATE is also compatible with other optimization methods like [DeepCache](./deepcache).
-
-Before you begin, make sure you install T-GATE.
-
-```bash
-pip install tgate
-pip install -U pytorch diffusers transformers accelerate DeepCache
-```
-
-
-To use T-GATE with a pipeline, you need to use its corresponding loader.
-
-| Pipeline | T-GATE Loader |
-|---|---|
-| PixArt | TgatePixArtLoader |
-| Stable Diffusion XL | TgateSDXLLoader |
-| Stable Diffusion XL + DeepCache | TgateSDXLDeepCacheLoader |
-| Stable Diffusion | TgateSDLoader |
-| Stable Diffusion + DeepCache | TgateSDDeepCacheLoader |
-
-Next, create a `TgateLoader` with a pipeline, the gate step (the time step to stop calculating the cross attention), and the number of inference steps. Then call the `tgate` method on the pipeline with a prompt, gate step, and the number of inference steps.
-
-Let's see how to enable this for several different pipelines.
-
-<hfoptions id="pipelines">
-<hfoption id="PixArt">
-
-Accelerate `PixArtAlphaPipeline` with T-GATE:
-
-```py
-import torch
-from diffusers import PixArtAlphaPipeline
-from tgate import TgatePixArtLoader
-
-pipe = PixArtAlphaPipeline.from_pretrained("PixArt-alpha/PixArt-XL-2-1024-MS", torch_dtype=torch.float16)
-
-gate_step = 8
-inference_step = 25
-pipe = TgatePixArtLoader(
-       pipe,
-       gate_step=gate_step,
-       num_inference_steps=inference_step,
-).to("cuda")
-
-image = pipe.tgate(
-       "An alpaca made of colorful building blocks, cyberpunk.",
-        gate_step=gate_step,
-       num_inference_steps=inference_step,
-).images[0]
-```
-</hfoption>
-<hfoption id="Stable Diffusion XL"> 
-
-Accelerate `StableDiffusionXLPipeline` with T-GATE:
-
-```py
-import torch
-from diffusers import StableDiffusionXLPipeline
-from diffusers import DPMSolverMultistepScheduler
-from tgate import TgateSDXLLoader
-
-pipe = StableDiffusionXLPipeline.from_pretrained(
-            "stabilityai/stable-diffusion-xl-base-1.0",
-            torch_dtype=torch.float16,
-            variant="fp16",
-            use_safetensors=True,
-)
-pipe.scheduler = DPMSolverMultistepScheduler.from_config(pipe.scheduler.config)
-
-gate_step = 10
-inference_step = 25
-pipe = TgateSDXLLoader(
-       pipe,
-       gate_step=gate_step,
-       num_inference_steps=inference_step,
-).to("cuda")
-
-image = pipe.tgate(
-        "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k.",
-        gate_step=gate_step,
-        num_inference_steps=inference_step
-).images[0]
-```
-</hfoption>
-<hfoption id="StableDiffusionXL with DeepCache">
-
-Accelerate `StableDiffusionXLPipeline` with [DeepCache](https://github.com/horseee/DeepCache) and T-GATE:
-
-```py
-import torch
-from diffusers import StableDiffusionXLPipeline
-from diffusers import DPMSolverMultistepScheduler
-from tgate import TgateSDXLDeepCacheLoader
-
-pipe = StableDiffusionXLPipeline.from_pretrained(
-            "stabilityai/stable-diffusion-xl-base-1.0",
-            torch_dtype=torch.float16,
-            variant="fp16",
-            use_safetensors=True,
-)
-pipe.scheduler = DPMSolverMultistepScheduler.from_config(pipe.scheduler.config)
-
-gate_step = 10
-inference_step = 25
-pipe = TgateSDXLDeepCacheLoader(
-       pipe,
-       cache_interval=3,
-       cache_branch_id=0,
-).to("cuda")
-
-image = pipe.tgate(
-        "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k.",
-        gate_step=gate_step,
-        num_inference_steps=inference_step
-).images[0]
-```
-</hfoption>
-<hfoption id="Latent Consistency Model">
-
-Accelerate `latent-consistency/lcm-sdxl` with T-GATE:
-
-```py
-import torch
-from diffusers import StableDiffusionXLPipeline
-from diffusers import UNet2DConditionModel, LCMScheduler
-from diffusers import DPMSolverMultistepScheduler
-from tgate import TgateSDXLLoader
-
-unet = UNet2DConditionModel.from_pretrained(
-    "latent-consistency/lcm-sdxl",
-    torch_dtype=torch.float16,
-    variant="fp16",
-)
-pipe = StableDiffusionXLPipeline.from_pretrained(
-    "stabilityai/stable-diffusion-xl-base-1.0",
-    unet=unet,
-    torch_dtype=torch.float16,
-    variant="fp16",
-)
-pipe.scheduler = LCMScheduler.from_config(pipe.scheduler.config)
-
-gate_step = 1
-inference_step = 4
-pipe = TgateSDXLLoader(
-       pipe,
-       gate_step=gate_step,
-       num_inference_steps=inference_step,
-       lcm=True
-).to("cuda")
-
-image = pipe.tgate(
-        "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k.",
-        gate_step=gate_step,
-        num_inference_steps=inference_step
-).images[0]
-```
-</hfoption>
-</hfoptions>
-
-T-GATE also supports [`StableDiffusionPipeline`] and [PixArt-alpha/PixArt-LCM-XL-2-1024-MS](https://hf.co/PixArt-alpha/PixArt-LCM-XL-2-1024-MS).
-
-## Benchmarks
-| Model                 | MACs     | Param     | Latency | Zero-shot 10K-FID on MS-COCO |
-|-----------------------|----------|-----------|---------|---------------------------|
-| SD-1.5                | 16.938T  | 859.520M  | 7.032s  | 23.927                    |
-| SD-1.5 w/ T-GATE       | 9.875T   | 815.557M  | 4.313s  | 20.789                    |
-| SD-2.1                | 38.041T  | 865.785M  | 16.121s | 22.609                    |
-| SD-2.1 w/ T-GATE       | 22.208T  | 815.433 M | 9.878s  | 19.940                    |
-| SD-XL                 | 149.438T | 2.570B    | 53.187s | 24.628                    |
-| SD-XL w/ T-GATE        | 84.438T  | 2.024B    | 27.932s | 22.738                    |
-| Pixart-Alpha          | 107.031T | 611.350M  | 61.502s | 38.669                    |
-| Pixart-Alpha w/ T-GATE | 65.318T  | 462.585M  | 37.867s | 35.825                    |
-| DeepCache (SD-XL)     | 57.888T  | -         | 19.931s | 23.755                    |
-| DeepCache w/ T-GATE    | 43.868T  | -         | 14.666s | 23.999                    |
-| LCM (SD-XL)           | 11.955T  | 2.570B    | 3.805s  | 25.044                    |
-| LCM w/ T-GATE          | 11.171T  | 2.024B    | 3.533s  | 25.028                    |
-| LCM (Pixart-Alpha)    | 8.563T   | 611.350M  | 4.733s  | 36.086                    |
-| LCM w/ T-GATE          | 7.623T   | 462.585M  | 4.543s  | 37.048                    |
-
-The latency is tested on an NVIDIA 1080TI, MACs and Params are calculated with [calflops](https://github.com/MrYxJ/calculate-flops.pytorch), and the FID is calculated with [PytorchFID](https://github.com/mseitzer/pytorch-fid).

docs/source/en/optimization/torch2.0.md

@@ -75,9 +75,6 @@ Compilation requires some time to complete, so it is best suited for situations
 
 For more information and different options about `torch.compile`, refer to the [`torch_compile`](https://pytorch.org/tutorials/intermediate/torch_compile_tutorial.html) tutorial.
 
-> [!TIP]
-> Learn more about other ways PyTorch 2.0 can help optimize your model in the [Accelerate inference of text-to-image diffusion models](../tutorials/fast_diffusion) tutorial.
-
 ## Benchmark
 
 We conducted a comprehensive benchmark with PyTorch 2.0's efficient attention implementation and `torch.compile` across different GPUs and batch sizes for five of our most used pipelines. The code is benchmarked on 🤗 Diffusers v0.17.0.dev0 to optimize `torch.compile` usage (see [here](https://github.com/huggingface/diffusers/pull/3313) for more details).

docs/source/en/training/controlnet.md

@@ -88,7 +88,7 @@ accelerate config default
 
 Or if your environment doesn't support an interactive shell, like a notebook, you can use:
 
-```py
+```bash
 from accelerate.utils import write_basic_config
 
 write_basic_config()

docs/source/en/training/custom_diffusion.md

@@ -54,7 +54,7 @@ accelerate config default
 
 Or if your environment doesn't support an interactive shell, like a notebook, you can use:
 
-```py
+```bash
 from accelerate.utils import write_basic_config
 
 write_basic_config()
@@ -84,7 +84,7 @@ Many of the basic parameters are described in the [DreamBooth](dreambooth#script
 - `--freeze_model`: freezes the key and value parameters in the cross-attention layer; the default is `crossattn_kv`, but you can set it to `crossattn` to train all the parameters in the cross-attention layer
 - `--concepts_list`: to learn multiple concepts, provide a path to a JSON file containing the concepts
 - `--modifier_token`: a special word used to represent the learned concept
-- `--initializer_token`: a special word used to initialize the embeddings of the `modifier_token`
+- `--initializer_token`:
 
 ### Prior preservation loss
 

docs/source/en/training/distributed_inference.md

@@ -52,76 +52,6 @@ To learn more, take a look at the [Distributed Inference with 🤗 Accelerate](h
 
 </Tip>
 
-### Device placement
-
-> [!WARNING]
-> This feature is experimental and its APIs might change in the future. 
-
-With Accelerate, you can use the `device_map` to determine how to distribute the models of a pipeline across multiple devices. This is useful in situations where you have more than one GPU.
-
-For example, if you have two 8GB GPUs, then using [`~DiffusionPipeline.enable_model_cpu_offload`] may not work so well because:
-
-* it only works on a single GPU
-* a single model might not fit on a single GPU ([`~DiffusionPipeline.enable_sequential_cpu_offload`] might work but it will be extremely slow and it is also limited to a single GPU)
-
-To make use of both GPUs, you can use the "balanced" device placement strategy which splits the models across all available GPUs.
-
-> [!WARNING]
-> Only the "balanced" strategy is supported at the moment, and we plan to support additional mapping strategies in the future.
-
-```diff
-from diffusers import DiffusionPipeline
-import torch
-
-pipeline = DiffusionPipeline.from_pretrained(
--    "runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16, use_safetensors=True,
-+    "runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16, use_safetensors=True, device_map="balanced"
-)
-image = pipeline("a dog").images[0]
-image
-```
-
-You can also pass a dictionary to enforce the maximum GPU memory that can be used on each device:
-
-```diff
-from diffusers import DiffusionPipeline
-import torch
-
-max_memory = {0:"1GB", 1:"1GB"}
-pipeline = DiffusionPipeline.from_pretrained(
-    "runwayml/stable-diffusion-v1-5",
-    torch_dtype=torch.float16, 
-    use_safetensors=True, 
-    device_map="balanced",
-+   max_memory=max_memory
-)
-image = pipeline("a dog").images[0]
-image
-```
-
-If a device is not present in `max_memory`, then it will be completely ignored and will not participate in the device placement. 
-
-By default, Diffusers uses the maximum memory of all devices. If the models don't fit on the GPUs, they are offloaded to the CPU. If the CPU doesn't have enough memory, then you might see an error. In that case, you could defer to using [`~DiffusionPipeline.enable_sequential_cpu_offload`] and [`~DiffusionPipeline.enable_model_cpu_offload`].
-
-Call [`~DiffusionPipeline.reset_device_map`] to reset the `device_map` of a pipeline. This is also necessary if you want to use methods like `to()`, [`~DiffusionPipeline.enable_sequential_cpu_offload`], and [`~DiffusionPipeline.enable_model_cpu_offload`] on a pipeline that was device-mapped.
-
-```py
-pipeline.reset_device_map()
-```
-
-Once a pipeline has been device-mapped, you can also access its device map via `hf_device_map`:
-
-```py
-print(pipeline.hf_device_map)
-```
-
-An example device map would look like so:
-
-
-```bash
-{'unet': 1, 'vae': 1, 'safety_checker': 0, 'text_encoder': 0}
-```
-
 ## PyTorch Distributed
 
 PyTorch supports [`DistributedDataParallel`](https://pytorch.org/docs/stable/generated/torch.nn.parallel.DistributedDataParallel.html) which enables data parallelism.

docs/source/en/training/dreambooth.md

@@ -67,7 +67,7 @@ accelerate config default
 
 Or if your environment doesn't support an interactive shell, like a notebook, you can use:
 
-```py
+```bash
 from accelerate.utils import write_basic_config
 
 write_basic_config()
@@ -180,7 +180,7 @@ elif args.pretrained_model_name_or_path:
         revision=args.revision,
         use_fast=False,
     )
-
+    
 # Load scheduler and models
 noise_scheduler = DDPMScheduler.from_pretrained(args.pretrained_model_name_or_path, subfolder="scheduler")
 text_encoder = text_encoder_cls.from_pretrained(

docs/source/en/training/instructpix2pix.md

@@ -51,7 +51,7 @@ accelerate config default
 
 Or if your environment doesn't support an interactive shell, like a notebook, you can use:
 
-```py
+```bash
 from accelerate.utils import write_basic_config
 
 write_basic_config()
@@ -89,7 +89,7 @@ The dataset preprocessing code and training loop are found in the [`main()`](htt
 
 As with the script parameters, a walkthrough of the training script is provided in the [Text-to-image](text2image#training-script) training guide. Instead, this guide takes a look at the InstructPix2Pix relevant parts of the script.
 
-The script begins by modifying the [number of input channels](https://github.com/huggingface/diffusers/blob/64603389da01082055a901f2883c4810d1144edb/examples/instruct_pix2pix/train_instruct_pix2pix.py#L445) in the first convolutional layer of the UNet to account for InstructPix2Pix's additional conditioning image:
+The script begins by modifing the [number of input channels](https://github.com/huggingface/diffusers/blob/64603389da01082055a901f2883c4810d1144edb/examples/instruct_pix2pix/train_instruct_pix2pix.py#L445) in the first convolutional layer of the UNet to account for InstructPix2Pix's additional conditioning image:
 
 ```py
 in_channels = 8

docs/source/en/training/kandinsky.md

@@ -59,7 +59,7 @@ accelerate config default
 
 Or if your environment doesn't support an interactive shell, like a notebook, you can use:
 
-```py
+```bash
 from accelerate.utils import write_basic_config
 
 write_basic_config()
@@ -235,7 +235,7 @@ accelerate launch --mixed_precision="fp16"  train_text_to_image_prior.py \
   --validation_prompts="A robot pokemon, 4k photo" \
   --report_to="wandb" \
   --push_to_hub \
-  --output_dir="kandi2-prior-pokemon-model"
+  --output_dir="kandi2-prior-pokemon-model" 
 ```
 
 </hfoption>
@@ -259,7 +259,7 @@ accelerate launch --mixed_precision="fp16"  train_text_to_image_decoder.py \
   --validation_prompts="A robot pokemon, 4k photo" \
   --report_to="wandb" \
   --push_to_hub \
-  --output_dir="kandi2-decoder-pokemon-model"
+  --output_dir="kandi2-decoder-pokemon-model" 
 ```
 
 </hfoption>

docs/source/en/training/lcm_distill.md

@@ -53,7 +53,7 @@ accelerate config default
 
 Or if your environment doesn't support an interactive shell, like a notebook, you can use:
 
-```py
+```bash
 from accelerate.utils import write_basic_config
 
 write_basic_config()
@@ -252,4 +252,4 @@ The SDXL training script is discussed in more detail in the [SDXL training](sdxl
 Congratulations on distilling a LCM model! To learn more about LCM, the following may be helpful:
 
 - Learn how to use [LCMs for inference](../using-diffusers/lcm) for text-to-image, image-to-image, and with LoRA checkpoints.
-- Read the [SDXL in 4 steps with Latent Consistency LoRAs](https://huggingface.co/blog/lcm_lora) blog post to learn more about SDXL LCM-LoRA's for super fast inference, quality comparisons, benchmarks, and more.
+- Read the [SDXL in 4 steps with Latent Consistency LoRAs](https://huggingface.co/blog/lcm_lora) blog post to learn more about SDXL LCM-LoRA's for super fast inference, quality comparisons, benchmarks, and more.

docs/source/en/training/lora.md

@@ -77,7 +77,7 @@ accelerate config default
 
 Or if your environment doesn't support an interactive shell, like a notebook, you can use:
 
-```py
+```bash
 from accelerate.utils import write_basic_config
 
 write_basic_config()
@@ -113,50 +113,36 @@ The dataset preprocessing code and training loop are found in the [`main()`](htt
 
 As with the script parameters, a walkthrough of the training script is provided in the [Text-to-image](text2image#training-script) training guide. Instead, this guide takes a look at the LoRA relevant parts of the script.
 
-<hfoptions id="lora">
-<hfoption id="UNet">
-
-Diffusers uses [`~peft.LoraConfig`] from the [PEFT](https://hf.co/docs/peft) library to set up the parameters of the LoRA adapter such as the rank, alpha, and which modules to insert the LoRA weights into. The adapter is added to the UNet, and only the LoRA layers are filtered for optimization in `lora_layers`.
+The script begins by adding the [new LoRA weights](https://github.com/huggingface/diffusers/blob/dd9a5caf61f04d11c0fa9f3947b69ab0010c9a0f/examples/text_to_image/train_text_to_image_lora.py#L447) to the attention layers. This involves correctly configuring the weight size for each block in the UNet. You'll see the `rank` parameter is used to create the [`~models.attention_processor.LoRAAttnProcessor`]:
 
 ```py
-unet_lora_config = LoraConfig(
-    r=args.rank,
-    lora_alpha=args.rank,
-    init_lora_weights="gaussian",
-    target_modules=["to_k", "to_q", "to_v", "to_out.0"],
-)
+lora_attn_procs = {}
+for name in unet.attn_processors.keys():
+    cross_attention_dim = None if name.endswith("attn1.processor") else unet.config.cross_attention_dim
+    if name.startswith("mid_block"):
+        hidden_size = unet.config.block_out_channels[-1]
+    elif name.startswith("up_blocks"):
+        block_id = int(name[len("up_blocks.")])
+        hidden_size = list(reversed(unet.config.block_out_channels))[block_id]
+    elif name.startswith("down_blocks"):
+        block_id = int(name[len("down_blocks.")])
+        hidden_size = unet.config.block_out_channels[block_id]
 
-unet.add_adapter(unet_lora_config)
-lora_layers = filter(lambda p: p.requires_grad, unet.parameters())
+    lora_attn_procs[name] = LoRAAttnProcessor(
+        hidden_size=hidden_size,
+        cross_attention_dim=cross_attention_dim,
+        rank=args.rank,
+    )
+
+unet.set_attn_processor(lora_attn_procs)
+lora_layers = AttnProcsLayers(unet.attn_processors)
 ```
 
-</hfoption>
-<hfoption id="text encoder">
-
-Diffusers also supports finetuning the text encoder with LoRA from the [PEFT](https://hf.co/docs/peft) library when necessary such as finetuning Stable Diffusion XL (SDXL). The [`~peft.LoraConfig`] is used to configure the parameters of the LoRA adapter which are then added to the text encoder, and only the LoRA layers are filtered for training.
-
-```py
-text_lora_config = LoraConfig(
-    r=args.rank,
-    lora_alpha=args.rank,
-    init_lora_weights="gaussian",
-    target_modules=["q_proj", "k_proj", "v_proj", "out_proj"],
-)
-
-text_encoder_one.add_adapter(text_lora_config)
-text_encoder_two.add_adapter(text_lora_config)
-text_lora_parameters_one = list(filter(lambda p: p.requires_grad, text_encoder_one.parameters()))
-text_lora_parameters_two = list(filter(lambda p: p.requires_grad, text_encoder_two.parameters()))
-```
-
-</hfoption>
-</hfoptions>
-
-The [optimizer](https://github.com/huggingface/diffusers/blob/e4b8f173b97731686e290b2eb98e7f5df2b1b322/examples/text_to_image/train_text_to_image_lora.py#L529) is initialized with the `lora_layers` because these are the only weights that'll be optimized:
+The [optimizer](https://github.com/huggingface/diffusers/blob/dd9a5caf61f04d11c0fa9f3947b69ab0010c9a0f/examples/text_to_image/train_text_to_image_lora.py#L519) is initialized with the `lora_layers` because these are the only weights that'll be optimized:
 
 ```py
 optimizer = optimizer_cls(
-    lora_layers,
+    lora_layers.parameters(),
     lr=args.learning_rate,
     betas=(args.adam_beta1, args.adam_beta2),
     weight_decay=args.adam_weight_decay,
@@ -170,7 +156,7 @@ Aside from setting up the LoRA layers, the training script is more or less the s
 
 Once you've made all your changes or you're okay with the default configuration, you're ready to launch the training script! 🚀
 
-Let's train on the [Pokémon BLIP captions](https://huggingface.co/datasets/lambdalabs/pokemon-blip-captions) dataset to generate our own Pokémon. Set the environment variables `MODEL_NAME` and `DATASET_NAME` to the model and dataset respectively. You should also specify where to save the model in `OUTPUT_DIR`, and the name of the model to save to on the Hub with `HUB_MODEL_ID`. The script creates and saves the following files to your repository:
+Let's train on the [Pokémon BLIP captions](https://huggingface.co/datasets/lambdalabs/pokemon-blip-captions) dataset to generate our yown Pokémon. Set the environment variables `MODEL_NAME` and `DATASET_NAME` to the model and dataset respectively. You should also specify where to save the model in `OUTPUT_DIR`, and the name of the model to save to on the Hub with `HUB_MODEL_ID`. The script creates and saves the following files to your repository:
 
 - saved model checkpoints
 - `pytorch_lora_weights.safetensors` (the trained LoRA weights)

docs/source/en/training/sdxl.md

@@ -59,7 +59,7 @@ accelerate config default
 
 Or if your environment doesn't support an interactive shell, like a notebook, you can use:
 
-```py
+```bash
 from accelerate.utils import write_basic_config
 
 write_basic_config()

docs/source/en/training/t2i_adapters.md

@@ -53,7 +53,7 @@ accelerate config default
 
 Or if your environment doesn't support an interactive shell, like a notebook, you can use:
 
-```py
+```bash
 from accelerate.utils import write_basic_config
 
 write_basic_config()

docs/source/en/training/text2image.md

@@ -69,7 +69,7 @@ accelerate config default
 
 Or if your environment doesn't support an interactive shell, like a notebook, you can use:
 
-```py
+```bash
 from accelerate.utils import write_basic_config
 
 write_basic_config()

docs/source/en/training/text_inversion.md

@@ -67,7 +67,7 @@ accelerate config default
 
 Or if your environment doesn't support an interactive shell, like a notebook, you can use:
 
-```py
+```bash
 from accelerate.utils import write_basic_config
 
 write_basic_config()

docs/source/en/training/unconditional_training.md

@@ -51,7 +51,7 @@ accelerate config default
 
 Or if your environment doesn't support an interactive shell like a notebook, you can use:
 
-```py
+```bash
 from accelerate.utils import write_basic_config
 
 write_basic_config()

docs/source/en/training/wuerstchen.md

@@ -53,7 +53,7 @@ accelerate config default
 
 Or if your environment doesn't support an interactive shell, like a notebook, you can use:
 
-```py
+```bash
 from accelerate.utils import write_basic_config
 
 write_basic_config()
@@ -173,7 +173,7 @@ pipeline = AutoPipelineForText2Image.from_pretrained("path/to/saved/model", torc
 
 caption = "A cute bird pokemon holding a shield"
 images = pipeline(
-    caption,
+    caption, 
     width=1024,
     height=1536,
     prior_timesteps=DEFAULT_STAGE_C_TIMESTEPS,

docs/source/en/tutorials/using_peft_for_inference.md

@@ -14,17 +14,19 @@ specific language governing permissions and limitations under the License.
 
 # Load LoRAs for inference
 
-There are many adapter types (with [LoRAs](https://huggingface.co/docs/peft/conceptual_guides/adapter#low-rank-adaptation-lora) being the most popular) trained in different styles to achieve different effects. You can even combine multiple adapters to create new and unique images.
+There are many adapters (with LoRAs being the most common type) trained in different styles to achieve different effects. You can even combine multiple adapters to create new and unique images. With the 🤗 [PEFT](https://huggingface.co/docs/peft/index) integration in 🤗 Diffusers, it is really easy to load and manage adapters for inference. In this guide, you'll learn how to use different adapters with [Stable Diffusion XL (SDXL)](../api/pipelines/stable_diffusion/stable_diffusion_xl) for inference.
 
-In this tutorial, you'll learn how to easily load and manage adapters for inference with the 🤗 [PEFT](https://huggingface.co/docs/peft/index) integration in 🤗 Diffusers. You'll use LoRA as the main adapter technique, so you'll see the terms LoRA and adapter used interchangeably.
+Throughout this guide, you'll use LoRA as the main adapter technique, so we'll use the terms LoRA and adapter interchangeably. You should have some familiarity with LoRA, and if you don't, we welcome you to check out the [LoRA guide](https://huggingface.co/docs/peft/conceptual_guides/lora).
 
 Let's first install all the required libraries.
 
 ```bash
-!pip install -q transformers accelerate peft diffusers
+!pip install -q transformers accelerate
+!pip install peft
+!pip install diffusers
 ```
 
-Now, load a pipeline with a [Stable Diffusion XL (SDXL)](../api/pipelines/stable_diffusion/stable_diffusion_xl) checkpoint:
+Now, let's load a pipeline with a SDXL checkpoint:
 
 ```python
 from diffusers import DiffusionPipeline
@@ -34,18 +36,21 @@ pipe_id = "stabilityai/stable-diffusion-xl-base-1.0"
 pipe = DiffusionPipeline.from_pretrained(pipe_id, torch_dtype=torch.float16).to("cuda")
 ```
 
-Next, load a [CiroN2022/toy-face](https://huggingface.co/CiroN2022/toy-face) adapter with the [`~diffusers.loaders.StableDiffusionXLLoraLoaderMixin.load_lora_weights`] method. With the 🤗 PEFT integration, you can assign a specific `adapter_name` to the checkpoint, which let's you easily switch between different LoRA checkpoints. Let's call this adapter `"toy"`.
+
+Next, load a LoRA checkpoint with the [`~diffusers.loaders.StableDiffusionXLLoraLoaderMixin.load_lora_weights`] method.
+
+With the 🤗 PEFT integration, you can assign a specific `adapter_name` to the checkpoint, which let's you easily switch between different LoRA checkpoints. Let's call this adapter `"toy"`.
 
 ```python
 pipe.load_lora_weights("CiroN2022/toy-face", weight_name="toy_face_sdxl.safetensors", adapter_name="toy")
 ```
 
-Make sure to include the token `toy_face` in the prompt and then you can perform inference:
+And then perform inference:
 
 ```python
 prompt = "toy_face of a hacker with a hoodie"
 
-lora_scale = 0.9
+lora_scale= 0.9
 image = pipe(
     prompt, num_inference_steps=30, cross_attention_kwargs={"scale": lora_scale}, generator=torch.manual_seed(0)
 ).images[0]
@@ -54,16 +59,17 @@ image
 
 ![toy-face](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/peft_integration/diffusers_peft_lora_inference_8_1.png)
 
-With the `adapter_name` parameter, it is really easy to use another adapter for inference! Load the [nerijs/pixel-art-xl](https://huggingface.co/nerijs/pixel-art-xl) adapter that has been fine-tuned to generate pixel art images and call it `"pixel"`.
 
-The pipeline automatically sets the first loaded adapter (`"toy"`) as the active adapter, but you can activate the `"pixel"` adapter with the [`~diffusers.loaders.UNet2DConditionLoadersMixin.set_adapters`] method:
+With the `adapter_name` parameter, it is really easy to use another adapter for inference! Load the [nerijs/pixel-art-xl](https://huggingface.co/nerijs/pixel-art-xl) adapter that has been fine-tuned to generate pixel art images, and let's call it `"pixel"`.
+
+The pipeline automatically sets the first loaded adapter (`"toy"`) as the active adapter. But you can activate the `"pixel"` adapter with the [`~diffusers.loaders.UNet2DConditionLoadersMixin.set_adapters`] method as shown below:
 
 ```python
 pipe.load_lora_weights("nerijs/pixel-art-xl", weight_name="pixel-art-xl.safetensors", adapter_name="pixel")
 pipe.set_adapters("pixel")
 ```
 
-Make sure you include the token `pixel art` in your prompt to generate a pixel art image:
+Let's now generate an image with the second adapter and check the result:
 
 ```python
 prompt = "a hacker with a hoodie, pixel art"
@@ -75,25 +81,29 @@ image
 
 ![pixel-art](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/peft_integration/diffusers_peft_lora_inference_12_1.png)
 
-## Merge adapters
+## Combine multiple adapters
 
-You can also merge different adapter checkpoints for inference to blend their styles together.
+You can also perform multi-adapter inference where you combine different adapter checkpoints for inference.
 
-Once again, use the [`~diffusers.loaders.UNet2DConditionLoadersMixin.set_adapters`] method to activate the `pixel` and `toy` adapters and specify the weights for how they should be merged.
+Once again, use the [`~diffusers.loaders.UNet2DConditionLoadersMixin.set_adapters`] method to activate two LoRA checkpoints and specify the weight for how the checkpoints should be combined.
 
 ```python
 pipe.set_adapters(["pixel", "toy"], adapter_weights=[0.5, 1.0])
 ```
 
+Now that we have set these two adapters, let's generate an image from the combined adapters!
+
 <Tip>
 
 LoRA checkpoints in the diffusion community are almost always obtained with [DreamBooth](https://huggingface.co/docs/diffusers/main/en/training/dreambooth). DreamBooth training often relies on "trigger" words in the input text prompts in order for the generation results to look as expected. When you combine multiple LoRA checkpoints, it's important to ensure the trigger words for the corresponding LoRA checkpoints are present in the input text prompts.
 
 </Tip>
 
-Remember to use the trigger words for [CiroN2022/toy-face](https://hf.co/CiroN2022/toy-face) and [nerijs/pixel-art-xl](https://hf.co/nerijs/pixel-art-xl) (these are found in their repositories) in the prompt to generate an image.
+The trigger words for [CiroN2022/toy-face](https://hf.co/CiroN2022/toy-face) and [nerijs/pixel-art-xl](https://hf.co/nerijs/pixel-art-xl) are found in their repositories.
+
 
 ```python
+# Notice how the prompt is constructed.
 prompt = "toy_face of a hacker with a hoodie, pixel art"
 image = pipe(
     prompt, num_inference_steps=30, cross_attention_kwargs={"scale": 1.0}, generator=torch.manual_seed(0)
@@ -103,95 +113,43 @@ image
 
 ![toy-face-pixel-art](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/peft_integration/diffusers_peft_lora_inference_16_1.png)
 
-Impressive! As you can see, the model generated an image that mixed the characteristics of both adapters.
+Impressive! As you can see, the model was able to generate an image that mixes the characteristics of both adapters.
 
-> [!TIP]
-> Through its PEFT integration, Diffusers also offers more efficient merging methods which you can learn about in the [Merge LoRAs](../using-diffusers/merge_loras) guide!
-
-To return to only using one adapter, use the [`~diffusers.loaders.UNet2DConditionLoadersMixin.set_adapters`] method to activate the `"toy"` adapter:
+If you want to go back to using only one adapter, use the [`~diffusers.loaders.UNet2DConditionLoadersMixin.set_adapters`] method to activate the `"toy"` adapter:
 
 ```python
+# First, set the adapter.
 pipe.set_adapters("toy")
 
+# Then, run inference.
 prompt = "toy_face of a hacker with a hoodie"
-lora_scale = 0.9
+lora_scale= 0.9
 image = pipe(
     prompt, num_inference_steps=30, cross_attention_kwargs={"scale": lora_scale}, generator=torch.manual_seed(0)
 ).images[0]
 image
 ```
 
-Or to disable all adapters entirely, use the [`~diffusers.loaders.UNet2DConditionLoadersMixin.disable_lora`] method to return the base model.
+![toy-face-again](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/peft_integration/diffusers_peft_lora_inference_18_1.png)
+
+
+If you want to switch to only the base model, disable all LoRAs with the [`~diffusers.loaders.UNet2DConditionLoadersMixin.disable_lora`] method.
+
 
 ```python
 pipe.disable_lora()
 
 prompt = "toy_face of a hacker with a hoodie"
+lora_scale= 0.9
 image = pipe(prompt, num_inference_steps=30, generator=torch.manual_seed(0)).images[0]
 image
 ```
 
 ![no-lora](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/peft_integration/diffusers_peft_lora_inference_20_1.png)
 
-### Customize adapters strength
-For even more customization, you can control how strongly the adapter affects each part of the pipeline. For this, pass a dictionary with the control strengths (called "scales") to [`~diffusers.loaders.UNet2DConditionLoadersMixin.set_adapters`].
+## Monitoring active adapters
 
-For example, here's how you can turn on the adapter for the `down` parts, but turn it off for the `mid` and `up` parts:
-```python
-pipe.enable_lora()  # enable lora again, after we disabled it above
-prompt = "toy_face of a hacker with a hoodie, pixel art"
-adapter_weight_scales = { "unet": { "down": 1, "mid": 0, "up": 0} }
-pipe.set_adapters("pixel", adapter_weight_scales)
-image = pipe(prompt, num_inference_steps=30, generator=torch.manual_seed(0)).images[0]
-image
-```
-
-![block-lora-text-and-down](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/peft_integration/diffusers_peft_lora_inference_block_down.png)
-
-Let's see how turning off the `down` part and turning on the `mid` and `up` part respectively changes the image.
-```python
-adapter_weight_scales = { "unet": { "down": 0, "mid": 1, "up": 0} }
-pipe.set_adapters("pixel", adapter_weight_scales)
-image = pipe(prompt, num_inference_steps=30, generator=torch.manual_seed(0)).images[0]
-image
-```
-
-![block-lora-text-and-mid](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/peft_integration/diffusers_peft_lora_inference_block_mid.png)
-
-```python
-adapter_weight_scales = { "unet": { "down": 0, "mid": 0, "up": 1} }
-pipe.set_adapters("pixel", adapter_weight_scales)
-image = pipe(prompt, num_inference_steps=30, generator=torch.manual_seed(0)).images[0]
-image
-```
-
-![block-lora-text-and-up](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/peft_integration/diffusers_peft_lora_inference_block_up.png)
-
-Looks cool!
-
-This is a really powerful feature. You can use it to control the adapter strengths down to per-transformer level. And you can even use it for multiple adapters.
-```python
-adapter_weight_scales_toy = 0.5
-adapter_weight_scales_pixel = {
-    "unet": {
-        "down": 0.9,  # all transformers in the down-part will use scale 0.9
-        # "mid"  # because, in this example, "mid" is not given, all transformers in the mid part will use the default scale 1.0
-        "up": {
-            "block_0": 0.6,  # all 3 transformers in the 0th block in the up-part will use scale 0.6
-            "block_1": [0.4, 0.8, 1.0],  # the 3 transformers in the 1st block in the up-part will use scales 0.4, 0.8 and 1.0 respectively
-        }
-    }
-}
-pipe.set_adapters(["toy", "pixel"], [adapter_weight_scales_toy, adapter_weight_scales_pixel])
-image = pipe(prompt, num_inference_steps=30, generator=torch.manual_seed(0)).images[0]
-image
-```
-
-![block-lora-mixed](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/peft_integration/diffusers_peft_lora_inference_block_mixed.png)
-
-## Manage active adapters
-
-You have attached multiple adapters in this tutorial, and if you're feeling a bit lost on what adapters have been attached to the pipeline's components, use the [`~diffusers.loaders.LoraLoaderMixin.get_active_adapters`] method to check the list of active adapters:
+You have attached multiple adapters in this tutorial, and if you're feeling a bit lost on what adapters have been attached to the pipeline's components, you can easily check the list of active adapters using the [`~diffusers.loaders.LoraLoaderMixin.get_active_adapters`] method:
 
 ```py
 active_adapters = pipe.get_active_adapters()
@@ -206,3 +164,74 @@ list_adapters_component_wise = pipe.get_list_adapters()
 list_adapters_component_wise
 {"text_encoder": ["toy", "pixel"], "unet": ["toy", "pixel"], "text_encoder_2": ["toy", "pixel"]}
 ```
+
+## Compatibility with `torch.compile`
+
+If you want to compile your model with `torch.compile` make sure to first fuse the LoRA weights into the base model and unload them.
+
+```py
+pipe.load_lora_weights("nerijs/pixel-art-xl", weight_name="pixel-art-xl.safetensors", adapter_name="pixel")
+pipe.load_lora_weights("CiroN2022/toy-face", weight_name="toy_face_sdxl.safetensors", adapter_name="toy")
+
+pipe.set_adapters(["pixel", "toy"], adapter_weights=[0.5, 1.0])
+# Fuses the LoRAs into the Unet
+pipe.fuse_lora()
+pipe.unload_lora_weights()
+
+pipe = torch.compile(pipe)
+
+prompt = "toy_face of a hacker with a hoodie, pixel art"
+image = pipe(prompt, num_inference_steps=30, generator=torch.manual_seed(0)).images[0]
+```
+
+## Fusing adapters into the model
+
+You can use PEFT to easily fuse/unfuse multiple adapters directly into the model weights (both UNet and text encoder) using the [`~diffusers.loaders.LoraLoaderMixin.fuse_lora`] method, which can lead to a speed-up in inference and lower VRAM usage.
+
+```py
+pipe.load_lora_weights("nerijs/pixel-art-xl", weight_name="pixel-art-xl.safetensors", adapter_name="pixel")
+pipe.load_lora_weights("CiroN2022/toy-face", weight_name="toy_face_sdxl.safetensors", adapter_name="toy")
+
+pipe.set_adapters(["pixel", "toy"], adapter_weights=[0.5, 1.0])
+# Fuses the LoRAs into the Unet
+pipe.fuse_lora()
+
+prompt = "toy_face of a hacker with a hoodie, pixel art"
+image = pipe(prompt, num_inference_steps=30, generator=torch.manual_seed(0)).images[0]
+
+# Gets the Unet back to the original state
+pipe.unfuse_lora()
+```
+
+You can also fuse some adapters using `adapter_names` for faster generation:
+
+```py
+pipe.load_lora_weights("nerijs/pixel-art-xl", weight_name="pixel-art-xl.safetensors", adapter_name="pixel")
+pipe.load_lora_weights("CiroN2022/toy-face", weight_name="toy_face_sdxl.safetensors", adapter_name="toy")
+
+pipe.set_adapters(["pixel"], adapter_weights=[0.5, 1.0])
+# Fuses the LoRAs into the Unet
+pipe.fuse_lora(adapter_names=["pixel"])
+
+prompt = "a hacker with a hoodie, pixel art"
+image = pipe(prompt, num_inference_steps=30, generator=torch.manual_seed(0)).images[0]
+
+# Gets the Unet back to the original state
+pipe.unfuse_lora()
+
+# Fuse all adapters
+pipe.fuse_lora(adapter_names=["pixel", "toy"])
+
+prompt = "toy_face of a hacker with a hoodie, pixel art"
+image = pipe(prompt, num_inference_steps=30, generator=torch.manual_seed(0)).images[0]
+```
+
+## Saving a pipeline after fusing the adapters
+
+To properly save a pipeline after it's been loaded with the adapters, it should be serialized like so:
+
+```python
+pipe.fuse_lora(lora_scale=1.0)
+pipe.unload_lora_weights()
+pipe.save_pretrained("path-to-pipeline")
+```

docs/source/en/using-diffusers/callback.md

@@ -12,18 +12,13 @@ specific language governing permissions and limitations under the License.
 
 # Pipeline callbacks
 
-The denoising loop of a pipeline can be modified with custom defined functions using the `callback_on_step_end` parameter. The callback function is executed at the end of each step, and modifies the pipeline attributes and variables for the next step. This is really useful for *dynamically* adjusting certain pipeline attributes or modifying tensor variables. This versatility allows for interesting use-cases such as changing the prompt embeddings at each timestep, assigning different weights to the prompt embeddings, and editing the guidance scale. With callbacks, you can implement new features without modifying the underlying code!
+The denoising loop of a pipeline can be modified with custom defined functions using the `callback_on_step_end` parameter. This can be really useful for *dynamically* adjusting certain pipeline attributes, or modifying tensor variables. The flexibility of callbacks opens up some interesting use-cases such as changing the prompt embeddings at each timestep, assigning different weights to the prompt embeddings, and editing the guidance scale.
 
-> [!TIP]
-> 🤗 Diffusers currently only supports `callback_on_step_end`, but feel free to open a [feature request](https://github.com/huggingface/diffusers/issues/new/choose) if you have a cool use-case and require a callback function with a different execution point!
+This guide will show you how to use the `callback_on_step_end` parameter to disable classifier-free guidance (CFG) after 40% of the inference steps to save compute with minimal cost to performance.
 
-This guide will demonstrate how callbacks work by a few features you can implement with them.
+The callback function should have the following arguments:
 
-## Dynamic classifier-free guidance
-
-Dynamic classifier-free guidance (CFG) is a feature that allows you to disable CFG after a certain number of inference steps which can help you save compute with minimal cost to performance. The callback function for this should have the following arguments:
-
-* `pipeline` (or the pipeline instance) provides access to important properties such as `num_timesteps` and `guidance_scale`. You can modify these properties by updating the underlying attributes. For this example, you'll disable CFG by setting `pipeline._guidance_scale=0.0`.
+* `pipe` (or the pipeline instance) provides access to useful properties such as `num_timesteps` and `guidance_scale`. You can modify these properties by updating the underlying attributes. For this example, you'll disable CFG by setting `pipe._guidance_scale=0.0`.
 * `step_index` and `timestep` tell you where you are in the denoising loop. Use `step_index` to turn off CFG after reaching 40% of `num_timesteps`.
 * `callback_kwargs` is a dict that contains tensor variables you can modify during the denoising loop. It only includes variables specified in the `callback_on_step_end_tensor_inputs` argument, which is passed to the pipeline's `__call__` method. Different pipelines may use different sets of variables, so please check a pipeline's `_callback_tensor_inputs` attribute for the list of variables you can modify. Some common variables include `latents` and `prompt_embeds`. For this function, change the batch size of `prompt_embeds` after setting `guidance_scale=0.0` in order for it to work properly.
 
@@ -32,13 +27,13 @@ Your callback function should look something like this:
 ```python
 def callback_dynamic_cfg(pipe, step_index, timestep, callback_kwargs):
         # adjust the batch_size of prompt_embeds according to guidance_scale
-        if step_index == int(pipeline.num_timesteps * 0.4):
+        if step_index == int(pipe.num_timesteps * 0.4):
                 prompt_embeds = callback_kwargs["prompt_embeds"]
                 prompt_embeds = prompt_embeds.chunk(2)[-1]
 
-                # update guidance_scale and prompt_embeds
-                pipeline._guidance_scale = 0.0
-                callback_kwargs["prompt_embeds"] = prompt_embeds
+        # update guidance_scale and prompt_embeds
+        pipe._guidance_scale = 0.0
+        callback_kwargs["prompt_embeds"] = prompt_embeds
         return callback_kwargs
 ```
 
@@ -48,134 +43,58 @@ Now, you can pass the callback function to the `callback_on_step_end` parameter
 import torch
 from diffusers import StableDiffusionPipeline
 
-pipeline = StableDiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16)
-pipeline = pipeline.to("cuda")
+pipe = StableDiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16)
+pipe = pipe.to("cuda")
 
 prompt = "a photo of an astronaut riding a horse on mars"
 
 generator = torch.Generator(device="cuda").manual_seed(1)
-out = pipeline(
-    prompt,
-    generator=generator,
-    callback_on_step_end=callback_dynamic_cfg,
-    callback_on_step_end_tensor_inputs=['prompt_embeds']
-)
+out = pipe(prompt, generator=generator, callback_on_step_end=callback_dynamic_cfg, callback_on_step_end_tensor_inputs=['prompt_embeds'])
 
 out.images[0].save("out_custom_cfg.png")
 ```
 
+The callback function is executed at the end of each denoising step, and modifies the pipeline attributes and tensor variables for the next denoising step.
+
+With callbacks, you can implement features such as dynamic CFG without having to modify the underlying code at all!
+
+<Tip>
+
+🤗 Diffusers currently only supports `callback_on_step_end`, but feel free to open a [feature request](https://github.com/huggingface/diffusers/issues/new/choose) if you have a cool use-case and require a callback function with a different execution point!
+
+</Tip>
+
 ## Interrupt the diffusion process
 
-> [!TIP]
-> The interruption callback is supported for text-to-image, image-to-image, and inpainting for the [StableDiffusionPipeline](../api/pipelines/stable_diffusion/overview) and [StableDiffusionXLPipeline](../api/pipelines/stable_diffusion/stable_diffusion_xl).
+Interrupting the diffusion process is particularly useful when building UIs that work with Diffusers because it allows users to stop the generation process if they're unhappy with the intermediate results. You can incorporate this into your pipeline with a callback.
 
-Stopping the diffusion process early is useful when building UIs that work with Diffusers because it allows users to stop the generation process if they're unhappy with the intermediate results. You can incorporate this into your pipeline with a callback.
+<Tip>
 
-This callback function should take the following arguments: `pipeline`, `i`, `t`, and `callback_kwargs` (this must be returned). Set the pipeline's `_interrupt` attribute to `True` to stop the diffusion process after a certain number of steps. You are also free to implement your own custom stopping logic inside the callback.
+The interruption callback is supported for text-to-image, image-to-image, and inpainting for the [StableDiffusionPipeline](../api/pipelines/stable_diffusion/overview) and [StableDiffusionXLPipeline](../api/pipelines/stable_diffusion/stable_diffusion_xl).
+
+</Tip>
+
+This callback function should take the following arguments: `pipe`, `i`, `t`, and `callback_kwargs` (this must be returned). Set the pipeline's `_interrupt` attribute to `True` to stop the diffusion process after a certain number of steps. You are also free to implement your own custom stopping logic inside the callback.
 
 In this example, the diffusion process is stopped after 10 steps even though `num_inference_steps` is set to 50.
 
 ```python
 from diffusers import StableDiffusionPipeline
 
-pipeline = StableDiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5")
-pipeline.enable_model_cpu_offload()
+pipe = StableDiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5")
+pipe.enable_model_cpu_offload()
 num_inference_steps = 50
 
-def interrupt_callback(pipeline, i, t, callback_kwargs):
+def interrupt_callback(pipe, i, t, callback_kwargs):
     stop_idx = 10
     if i == stop_idx:
-        pipeline._interrupt = True
+        pipe._interrupt = True
 
     return callback_kwargs
 
-pipeline(
+pipe(
     "A photo of a cat",
     num_inference_steps=num_inference_steps,
     callback_on_step_end=interrupt_callback,
 )
 ```
-
-## Display image after each generation step
-
-> [!TIP]
-> This tip was contributed by [asomoza](https://github.com/asomoza).
-
-Display an image after each generation step by accessing and converting the latents after each step into an image. The latent space is compressed to 128x128, so the images are also 128x128 which is useful for a quick preview.
-
-1. Use the function below to convert the SDXL latents (4 channels) to RGB tensors (3 channels) as explained in the [Explaining the SDXL latent space](https://huggingface.co/blog/TimothyAlexisVass/explaining-the-sdxl-latent-space) blog post.
-
-```py
-def latents_to_rgb(latents):
-    weights = (
-        (60, -60, 25, -70),
-        (60,  -5, 15, -50),
-        (60,  10, -5, -35)
-    )
-
-    weights_tensor = torch.t(torch.tensor(weights, dtype=latents.dtype).to(latents.device))
-    biases_tensor = torch.tensor((150, 140, 130), dtype=latents.dtype).to(latents.device)
-    rgb_tensor = torch.einsum("...lxy,lr -> ...rxy", latents, weights_tensor) + biases_tensor.unsqueeze(-1).unsqueeze(-1)
-    image_array = rgb_tensor.clamp(0, 255)[0].byte().cpu().numpy()
-    image_array = image_array.transpose(1, 2, 0)
-
-    return Image.fromarray(image_array)
-```
-
-2. Create a function to decode and save the latents into an image.
-
-```py
-def decode_tensors(pipe, step, timestep, callback_kwargs):
-    latents = callback_kwargs["latents"]
-    
-    image = latents_to_rgb(latents)
-    image.save(f"{step}.png")
-
-    return callback_kwargs
-```
-
-3. Pass the `decode_tensors` function to the `callback_on_step_end` parameter to decode the tensors after each step. You also need to specify what you want to modify in the `callback_on_step_end_tensor_inputs` parameter, which in this case are the latents.
-
-```py
-from diffusers import AutoPipelineForText2Image
-import torch
-from PIL import Image
-
-pipeline = AutoPipelineForText2Image.from_pretrained(
-    "stabilityai/stable-diffusion-xl-base-1.0",
-    torch_dtype=torch.float16,
-    variant="fp16",
-    use_safetensors=True
-).to("cuda")
-
-image = pipeline(
-    prompt="A croissant shaped like a cute bear.",
-    negative_prompt="Deformed, ugly, bad anatomy",
-    callback_on_step_end=decode_tensors,
-    callback_on_step_end_tensor_inputs=["latents"],
-).images[0]
-```
-
-<div class="flex gap-4 justify-center">
-  <div>
-    <img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/tips_step_0.png"/>
-    <figcaption class="mt-2 text-center text-sm text-gray-500">step 0</figcaption>
-  </div>
-  <div>
-    <img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/tips_step_19.png"/>
-    <figcaption class="mt-2 text-center text-sm text-gray-500">step 19
-    </figcaption>
-  </div>
-  <div>
-    <img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/tips_step_29.png"/>
-    <figcaption class="mt-2 text-center text-sm text-gray-500">step 29</figcaption>
-  </div>
-  <div>
-    <img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/tips_step_39.png"/>
-    <figcaption class="mt-2 text-center text-sm text-gray-500">step 39</figcaption>
-  </div>
-  <div>
-    <img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/tips_step_49.png"/>
-    <figcaption class="mt-2 text-center text-sm text-gray-500">step 49</figcaption>
-  </div>
-</div>

docs/source/en/using-diffusers/controlnet.md

@@ -429,27 +429,6 @@ image = pipe(
 make_image_grid([original_image, canny_image, image], rows=1, cols=3)
 ```
 
-<Tip>
-
-You can use a refiner model with `StableDiffusionXLControlNetPipeline` to improve image quality, just like you can with a regular `StableDiffusionXLPipeline`.
-See the [Refine image quality](./sdxl#refine-image-quality) section to learn how to use the refiner model.
-Make sure to use `StableDiffusionXLControlNetPipeline` and pass `image` and `controlnet_conditioning_scale`.
-
-```py
-base = StableDiffusionXLControlNetPipeline(...)
-image = base(
-    prompt=prompt,
-    controlnet_conditioning_scale=0.5,
-    image=canny_image,
-    num_inference_steps=40,
-    denoising_end=0.8,
-    output_type="latent",
-).images
-# rest exactly as with StableDiffusionXLPipeline
-```
-
-</Tip>
-
 ## MultiControlNet
 
 <Tip>

docs/source/en/using-diffusers/custom_pipeline_overview.md

@@ -16,19 +16,17 @@ specific language governing permissions and limitations under the License.
 
 ## Community pipelines
 
-Community pipelines are any [`DiffusionPipeline`] class that are different from the original paper implementation (for example, the [`StableDiffusionControlNetPipeline`] corresponds to the [Text-to-Image Generation with ControlNet Conditioning](https://arxiv.org/abs/2302.05543) paper). They provide additional functionality or extend the original implementation of a pipeline.
+Community pipelines are any [`DiffusionPipeline`] class that are different from the original implementation as specified in their paper (for example, the [`StableDiffusionControlNetPipeline`] corresponds to the [Text-to-Image Generation with ControlNet Conditioning](https://arxiv.org/abs/2302.05543) paper). They provide additional functionality or extend the original implementation of a pipeline.
 
-There are many cool community pipelines like [Marigold Depth Estimation](https://github.com/huggingface/diffusers/tree/main/examples/community#marigold-depth-estimation) or [InstantID](https://github.com/huggingface/diffusers/tree/main/examples/community#instantid-pipeline), and you can find all the official community pipelines [here](https://github.com/huggingface/diffusers/tree/main/examples/community).
+There are many cool community pipelines like [Speech to Image](https://github.com/huggingface/diffusers/tree/main/examples/community#speech-to-image) or [Composable Stable Diffusion](https://github.com/huggingface/diffusers/tree/main/examples/community#composable-stable-diffusion), and you can find all the official community pipelines [here](https://github.com/huggingface/diffusers/tree/main/examples/community).
 
-There are two types of community pipelines, those stored on the Hugging Face Hub and those stored on Diffusers GitHub repository. Hub pipelines are completely customizable (scheduler, models, pipeline code, etc.) while Diffusers GitHub pipelines are only limited to custom pipeline code. Refer to this [table](./contribute_pipeline#share-your-pipeline) for a more detailed comparison of Hub vs GitHub community pipelines.
+To load any community pipeline on the Hub, pass the repository id of the community pipeline to the `custom_pipeline` argument and the model repository where you'd like to load the pipeline weights and components from. For example, the example below loads a dummy pipeline from [`hf-internal-testing/diffusers-dummy-pipeline`](https://huggingface.co/hf-internal-testing/diffusers-dummy-pipeline/blob/main/pipeline.py) and the pipeline weights and components from [`google/ddpm-cifar10-32`](https://huggingface.co/google/ddpm-cifar10-32):
 
-<hfoptions id="community">
-<hfoption id="Hub pipelines">
+<Tip warning={true}>
 
-To load a Hugging Face Hub community pipeline, pass the repository id of the community pipeline to the `custom_pipeline` argument and the model repository where you'd like to load the pipeline weights and components from. For example, the example below loads a dummy pipeline from [hf-internal-testing/diffusers-dummy-pipeline](https://huggingface.co/hf-internal-testing/diffusers-dummy-pipeline/blob/main/pipeline.py) and the pipeline weights and components from [google/ddpm-cifar10-32](https://huggingface.co/google/ddpm-cifar10-32):
+🔒 By loading a community pipeline from the Hugging Face Hub, you are trusting that the code you are loading is safe. Make sure to inspect the code online before loading and running it automatically!
 
-> [!WARNING]
-> By loading a community pipeline from the Hugging Face Hub, you are trusting that the code you are loading is safe. Make sure to inspect the code online before loading and running it automatically!
+</Tip>
 
 ```py
 from diffusers import DiffusionPipeline
@@ -38,10 +36,7 @@ pipeline = DiffusionPipeline.from_pretrained(
 )
 ```
 
-</hfoption>
-<hfoption id="GitHub pipelines">
-
-To load a GitHub community pipeline, pass the repository id of the community pipeline to the `custom_pipeline` argument and the model repository where you you'd like to load the pipeline weights and components from. You can also load model components directly. The example below loads the community [CLIP Guided Stable Diffusion](https://github.com/huggingface/diffusers/tree/main/examples/community#clip-guided-stable-diffusion) pipeline and the CLIP model components.
+Loading an official community pipeline is similar, but you can mix loading weights from an official repository id and pass pipeline components directly. The example below loads the community [CLIP Guided Stable Diffusion](https://github.com/huggingface/diffusers/tree/main/examples/community#clip-guided-stable-diffusion) pipeline, and you can pass the CLIP model components directly to it:
 
 ```py
 from diffusers import DiffusionPipeline
@@ -61,12 +56,9 @@ pipeline = DiffusionPipeline.from_pretrained(
 )
 ```
 
-</hfoption>
-</hfoptions>
-
 ### Load from a local file
 
-Community pipelines can also be loaded from a local file if you pass a file path instead. The path to the passed directory must contain a pipeline.py file that contains the pipeline class.
+Community pipelines can also be loaded from a local file if you pass a file path instead. The path to the passed directory must contain a `pipeline.py` file that contains the pipeline class in order to successfully load it.
 
 ```py
 pipeline = DiffusionPipeline.from_pretrained(
@@ -85,7 +77,7 @@ By default, community pipelines are loaded from the latest stable version of Dif
 <hfoptions id="version">
 <hfoption id="main">
 
-For example, to load from the main branch:
+For example, to load from the `main` branch:
 
 ```py
 pipeline = DiffusionPipeline.from_pretrained(
@@ -101,7 +93,7 @@ pipeline = DiffusionPipeline.from_pretrained(
 </hfoption>
 <hfoption id="older version">
 
-For example, to load from a previous version of Diffusers like v0.25.0:
+For example, to load from a previous version of Diffusers like `v0.25.0`:
 
 ```py
 pipeline = DiffusionPipeline.from_pretrained(
@@ -117,49 +109,8 @@ pipeline = DiffusionPipeline.from_pretrained(
 </hfoption>
 </hfoptions>
 
-### Load with from_pipe
 
-Community pipelines can also be loaded with the [`~DiffusionPipeline.from_pipe`] method which allows you to load and reuse multiple pipelines without any additional memory overhead (learn more in the [Reuse a pipeline](./loading#reuse-a-pipeline) guide). The memory requirement is determined by the largest single pipeline loaded.
-
-For example, let's load a community pipeline that supports [long prompts with weighting](https://github.com/huggingface/diffusers/tree/main/examples/community#long-prompt-weighting-stable-diffusion) from a Stable Diffusion pipeline.
-
-```py
-import torch
-from diffusers import DiffusionPipeline
-
-pipe_sd = DiffusionPipeline.from_pretrained("emilianJR/CyberRealistic_V3", torch_dtype=torch.float16)
-pipe_sd.to("cuda")
-# load long prompt weighting pipeline
-pipe_lpw = DiffusionPipeline.from_pipe(
-    pipe_sd,
-    custom_pipeline="lpw_stable_diffusion",
-).to("cuda")
-
-prompt = "cat, hiding in the leaves, ((rain)), zazie rainyday, beautiful eyes, macro shot, colorful details, natural lighting, amazing composition, subsurface scattering, amazing textures, filmic, soft light, ultra-detailed eyes, intricate details, detailed texture, light source contrast, dramatic shadows, cinematic light, depth of field, film grain, noise, dark background, hyperrealistic dslr film still, dim volumetric cinematic lighting"
-neg_prompt = "(deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime, mutated hands and fingers:1.4), (deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, amputation"
-generator = torch.Generator(device="cpu").manual_seed(20)
-out_lpw = pipe_lpw(
-    prompt, 
-    negative_prompt=neg_prompt, 
-    width=512,
-    height=512,
-    max_embeddings_multiples=3, 
-    num_inference_steps=50,
-    generator=generator,
-    ).images[0]
-out_lpw
-```
-
-<div class="flex gap-4">
-  <div>
-    <img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/from_pipe_lpw.png" />
-    <figcaption class="mt-2 text-center text-sm text-gray-500">Stable Diffusion with long prompt weighting</figcaption>
-  </div>
-  <div>
-    <img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/from_pipe_non_lpw.png" />
-    <figcaption class="mt-2 text-center text-sm text-gray-500">Stable Diffusion</figcaption>
-  </div>
-</div>
+For more information about community pipelines, take a look at the [Community pipelines](custom_pipeline_examples) guide for how to use them and if you're interested in adding a community pipeline check out the [How to contribute a community pipeline](contribute_pipeline) guide!
 
 ## Community components
 
@@ -167,7 +118,7 @@ Community components allow users to build pipelines that may have customized com
 
 This section shows how users should use community components to build a community pipeline.
 
-You'll use the [showlab/show-1-base](https://huggingface.co/showlab/show-1-base) pipeline checkpoint as an example.
+You'll use the [showlab/show-1-base](https://huggingface.co/showlab/show-1-base) pipeline checkpoint as an example. So, let's start loading the components:
 
 1. Import and load the text encoder from Transformers:
 
@@ -201,17 +152,17 @@ In steps 4 and 5, the custom [UNet](https://github.com/showlab/Show-1/blob/main/
 
 </Tip>
 
-4. Now you'll load a [custom UNet](https://github.com/showlab/Show-1/blob/main/showone/models/unet_3d_condition.py), which in this example, has already been implemented in [showone_unet_3d_condition.py](https://huggingface.co/sayakpaul/show-1-base-with-code/blob/main/unet/showone_unet_3d_condition.py) for your convenience. You'll notice the [`UNet3DConditionModel`] class name is changed to `ShowOneUNet3DConditionModel` because [`UNet3DConditionModel`] already exists in Diffusers. Any components needed for the `ShowOneUNet3DConditionModel` class should be placed in showone_unet_3d_condition.py.
+4. Now you'll load a [custom UNet](https://github.com/showlab/Show-1/blob/main/showone/models/unet_3d_condition.py), which in this example, has already been implemented in the `showone_unet_3d_condition.py` [script](https://huggingface.co/sayakpaul/show-1-base-with-code/blob/main/unet/showone_unet_3d_condition.py) for your convenience. You'll notice the `UNet3DConditionModel` class name is changed to `ShowOneUNet3DConditionModel` because [`UNet3DConditionModel`] already exists in Diffusers. Any components needed for the `ShowOneUNet3DConditionModel` class should be placed in the `showone_unet_3d_condition.py` script.
 
-    Once this is done, you can initialize the UNet:
+Once this is done, you can initialize the UNet:
 
-    ```python
-    from showone_unet_3d_condition import ShowOneUNet3DConditionModel
+```python
+from showone_unet_3d_condition import ShowOneUNet3DConditionModel
 
-    unet = ShowOneUNet3DConditionModel.from_pretrained(pipe_id, subfolder="unet")
-    ```
+unet = ShowOneUNet3DConditionModel.from_pretrained(pipe_id, subfolder="unet")
+```
 
-5. Finally, you'll load the custom pipeline code. For this example, it has already been created for you in [pipeline_t2v_base_pixel.py](https://huggingface.co/sayakpaul/show-1-base-with-code/blob/main/pipeline_t2v_base_pixel.py). This script contains a custom `TextToVideoIFPipeline` class for generating videos from text. Just like the custom UNet, any code needed for the custom pipeline to work should go in pipeline_t2v_base_pixel.py.
+5. Finally, you'll load the custom pipeline code. For this example, it has already been created for you in the `pipeline_t2v_base_pixel.py` [script](https://huggingface.co/sayakpaul/show-1-base-with-code/blob/main/pipeline_t2v_base_pixel.py). This script contains a custom `TextToVideoIFPipeline` class for generating videos from text. Just like the custom UNet, any code needed for the custom pipeline to work should go in the `pipeline_t2v_base_pixel.py` script. 
 
 Once everything is in place, you can initialize the `TextToVideoIFPipeline` with the `ShowOneUNet3DConditionModel`:
 
@@ -236,16 +187,13 @@ Push the pipeline to the Hub to share with the community!
 pipeline.push_to_hub("custom-t2v-pipeline")
 ```
 
-After the pipeline is successfully pushed, you need to make a few changes:
+After the pipeline is successfully pushed, you need a couple of changes:
 
-1. Change the `_class_name` attribute in [model_index.json](https://huggingface.co/sayakpaul/show-1-base-with-code/blob/main/model_index.json#L2) to `"pipeline_t2v_base_pixel"` and `"TextToVideoIFPipeline"`.
-2. Upload `showone_unet_3d_condition.py` to the [unet](https://huggingface.co/sayakpaul/show-1-base-with-code/blob/main/unet/showone_unet_3d_condition.py) subfolder.
-3. Upload `pipeline_t2v_base_pixel.py` to the pipeline [repository](https://huggingface.co/sayakpaul/show-1-base-with-code/tree/main).
+1. Change the `_class_name` attribute in [`model_index.json`](https://huggingface.co/sayakpaul/show-1-base-with-code/blob/main/model_index.json#L2) to `"pipeline_t2v_base_pixel"` and `"TextToVideoIFPipeline"`.
+2. Upload `showone_unet_3d_condition.py` to the `unet` [directory](https://huggingface.co/sayakpaul/show-1-base-with-code/blob/main/unet/showone_unet_3d_condition.py).
+3. Upload `pipeline_t2v_base_pixel.py` to the pipeline base [directory](https://huggingface.co/sayakpaul/show-1-base-with-code/blob/main/unet/showone_unet_3d_condition.py).
 
-To run inference, add the `trust_remote_code` argument while initializing the pipeline to handle all the "magic" behind the scenes.
-
-> [!WARNING]
-> As an additional precaution with `trust_remote_code=True`, we strongly encourage you to pass a commit hash to the `revision` parameter in [`~DiffusionPipeline.from_pretrained`] to make sure the code hasn't been updated with some malicious new lines of code (unless you fully trust the model owners).
+To run inference, simply add the `trust_remote_code` argument while initializing the pipeline to handle all the "magic" behind the scenes.
 
 ```python
 from diffusers import DiffusionPipeline
@@ -273,9 +221,10 @@ video_frames = pipeline(
 ).frames
 ```
 
-As an additional reference, take a look at the repository structure of [stabilityai/japanese-stable-diffusion-xl](https://huggingface.co/stabilityai/japanese-stable-diffusion-xl/) which also uses the `trust_remote_code` feature.
+As an additional reference example, you can refer to the repository structure of [stabilityai/japanese-stable-diffusion-xl](https://huggingface.co/stabilityai/japanese-stable-diffusion-xl/), that makes use of the `trust_remote_code` feature:
 
 ```python
+
 from diffusers import DiffusionPipeline
 import torch
 
@@ -283,4 +232,12 @@ pipeline = DiffusionPipeline.from_pretrained(
     "stabilityai/japanese-stable-diffusion-xl", trust_remote_code=True
 )
 pipeline.to("cuda")
-```
+
+# if using torch < 2.0
+# pipeline.enable_xformers_memory_efficient_attention()
+
+prompt = "柴犬、カラフルアート"
+
+image = pipeline(prompt=prompt).images[0]
+
+```

docs/source/en/using-diffusers/freeu.md

@@ -128,7 +128,7 @@ seed = 2023
 # The values come from
 # https://github.com/lyn-rgb/FreeU_Diffusers#video-pipelines
 pipe.enable_freeu(b1=1.2, b2=1.4, s1=0.9, s2=0.2)
-video_frames = pipe(prompt, height=320, width=576, num_frames=30, generator=torch.manual_seed(seed)).frames[0]
+video_frames = pipe(prompt, height=320, width=576, num_frames=30, generator=torch.manual_seed(seed)).frames
 export_to_video(video_frames, "astronaut_rides_horse.mp4")
 ```
 

docs/source/en/using-diffusers/inference_with_tcd_lora.md

@@ -1,438 +0,0 @@
-<!--Copyright 2024 The HuggingFace Team. All rights reserved.
-
-Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
-the License. You may obtain a copy of the License at
-
-http://www.apache.org/licenses/LICENSE-2.0
-
-Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
-an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
-specific language governing permissions and limitations under the License.
--->
-
-[[open-in-colab]]
-
-# Trajectory Consistency Distillation-LoRA
-
-Trajectory Consistency Distillation (TCD) enables a model to generate higher quality and more detailed images with fewer steps. Moreover, owing to the effective error mitigation during the distillation process, TCD demonstrates superior performance even under conditions of large inference steps.
-
-The major advantages of TCD are:
-
-- Better than Teacher: TCD demonstrates superior generative quality at both small and large inference steps and exceeds the performance of [DPM-Solver++(2S)](../../api/schedulers/multistep_dpm_solver) with Stable Diffusion XL (SDXL). There is no additional discriminator or LPIPS supervision included during TCD training.
-
-- Flexible Inference Steps: The inference steps for TCD sampling can be freely adjusted without adversely affecting the image quality.
-
-- Freely change detail level: During inference, the level of detail in the image can be adjusted with a single hyperparameter, *gamma*.
-
-> [!TIP]
-> For more technical details of TCD, please refer to the [paper](https://arxiv.org/abs/2402.19159) or official [project page](https://mhh0318.github.io/tcd/)).
-
-For large models like SDXL, TCD is trained with [LoRA](https://huggingface.co/docs/peft/conceptual_guides/adapter#low-rank-adaptation-lora) to reduce memory usage. This is also useful because you can reuse LoRAs between different finetuned models, as long as they share the same base model, without further training.
-
-
-
-This guide will show you how to perform inference with TCD-LoRAs for a variety of tasks like text-to-image and inpainting, as well as how you can easily combine TCD-LoRAs with other adapters. Choose one of the supported base model and it's corresponding TCD-LoRA checkpoint from the table below to get started.
-
-| Base model                                                                                      | TCD-LoRA checkpoint                                            |
-|-------------------------------------------------------------------------------------------------|----------------------------------------------------------------|
-| [stable-diffusion-v1-5](https://huggingface.co/runwayml/stable-diffusion-v1-5)                  | [TCD-SD15](https://huggingface.co/h1t/TCD-SD15-LoRA)           |
-| [stable-diffusion-2-1-base](https://huggingface.co/stabilityai/stable-diffusion-2-1-base)       | [TCD-SD21-base](https://huggingface.co/h1t/TCD-SD21-base-LoRA) |
-| [stable-diffusion-xl-base-1.0](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0) | [TCD-SDXL](https://huggingface.co/h1t/TCD-SDXL-LoRA)           |
-
-
-Make sure you have [PEFT](https://github.com/huggingface/peft) installed for better LoRA support.
-
-```bash
-pip install -U peft
-```
-
-## General tasks
-
-In this guide, let's use the [`StableDiffusionXLPipeline`] and the [`TCDScheduler`]. Use the [`~StableDiffusionPipeline.load_lora_weights`] method to load the SDXL-compatible TCD-LoRA weights.
-
-A few tips to keep in mind for TCD-LoRA inference are to:
-
-- Keep the `num_inference_steps` between 4 and 50
-- Set `eta` (used to control stochasticity at each step) between 0 and 1. You should use a higher `eta` when increasing the number of inference steps, but the downside is that a larger `eta` in [`TCDScheduler`] leads to blurrier images. A value of 0.3 is recommended to produce good results.
-
-<hfoptions id="tasks">
-<hfoption id="text-to-image">
-
-```python
-import torch
-from diffusers import StableDiffusionXLPipeline, TCDScheduler
-
-device = "cuda"
-base_model_id = "stabilityai/stable-diffusion-xl-base-1.0"
-tcd_lora_id = "h1t/TCD-SDXL-LoRA"
-
-pipe = StableDiffusionXLPipeline.from_pretrained(base_model_id, torch_dtype=torch.float16, variant="fp16").to(device)
-pipe.scheduler = TCDScheduler.from_config(pipe.scheduler.config)
-
-pipe.load_lora_weights(tcd_lora_id)
-pipe.fuse_lora()
-
-prompt = "Painting of the orange cat Otto von Garfield, Count of Bismarck-Schönhausen, Duke of Lauenburg, Minister-President of Prussia. Depicted wearing a Prussian Pickelhaube and eating his favorite meal - lasagna."
-
-image = pipe(
-    prompt=prompt,
-    num_inference_steps=4,
-    guidance_scale=0,
-    eta=0.3, 
-    generator=torch.Generator(device=device).manual_seed(0),
-).images[0]
-```
-
-![](https://github.com/jabir-zheng/TCD/raw/main/assets/demo_image.png)
-
-</hfoption>
-
-<hfoption id="inpainting">
-
-```python
-import torch
-from diffusers import AutoPipelineForInpainting, TCDScheduler
-from diffusers.utils import load_image, make_image_grid
-
-device = "cuda"
-base_model_id = "diffusers/stable-diffusion-xl-1.0-inpainting-0.1"
-tcd_lora_id = "h1t/TCD-SDXL-LoRA"
-
-pipe = AutoPipelineForInpainting.from_pretrained(base_model_id, torch_dtype=torch.float16, variant="fp16").to(device)
-pipe.scheduler = TCDScheduler.from_config(pipe.scheduler.config)
-
-pipe.load_lora_weights(tcd_lora_id)
-pipe.fuse_lora()
-
-img_url = "https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo.png"
-mask_url = "https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo_mask.png"
-
-init_image = load_image(img_url).resize((1024, 1024))
-mask_image = load_image(mask_url).resize((1024, 1024))
-
-prompt = "a tiger sitting on a park bench"
-
-image = pipe(
-  prompt=prompt,
-  image=init_image,
-  mask_image=mask_image,
-  num_inference_steps=8,
-  guidance_scale=0,
-  eta=0.3,
-  strength=0.99,  # make sure to use `strength` below 1.0
-  generator=torch.Generator(device=device).manual_seed(0),
-).images[0]
-
-grid_image = make_image_grid([init_image, mask_image, image], rows=1, cols=3)
-```
-
-![](https://github.com/jabir-zheng/TCD/raw/main/assets/inpainting_tcd.png)
-
-
-</hfoption>
-</hfoptions>
-
-## Community models
-
-TCD-LoRA also works with many community finetuned models and plugins. For example, load the [animagine-xl-3.0](https://huggingface.co/cagliostrolab/animagine-xl-3.0) checkpoint which is a community finetuned version of SDXL for generating anime images.
-
-```python
-import torch
-from diffusers import StableDiffusionXLPipeline, TCDScheduler
-
-device = "cuda"
-base_model_id = "cagliostrolab/animagine-xl-3.0"
-tcd_lora_id = "h1t/TCD-SDXL-LoRA"
-
-pipe = StableDiffusionXLPipeline.from_pretrained(base_model_id, torch_dtype=torch.float16, variant="fp16").to(device)
-pipe.scheduler = TCDScheduler.from_config(pipe.scheduler.config)
-
-pipe.load_lora_weights(tcd_lora_id)
-pipe.fuse_lora()
-
-prompt = "A man, clad in a meticulously tailored military uniform, stands with unwavering resolve. The uniform boasts intricate details, and his eyes gleam with determination. Strands of vibrant, windswept hair peek out from beneath the brim of his cap."
-
-image = pipe(
-    prompt=prompt,
-    num_inference_steps=8,
-    guidance_scale=0,
-    eta=0.3, 
-    generator=torch.Generator(device=device).manual_seed(0),
-).images[0]
-```
-
-![](https://github.com/jabir-zheng/TCD/raw/main/assets/animagine_xl.png)
-
-TCD-LoRA also supports other LoRAs trained on different styles. For example, let's load the [TheLastBen/Papercut_SDXL](https://huggingface.co/TheLastBen/Papercut_SDXL) LoRA and fuse it with the TCD-LoRA with the [`~loaders.UNet2DConditionLoadersMixin.set_adapters`] method. 
-
-> [!TIP]
-> Check out the [Merge LoRAs](merge_loras) guide to learn more about efficient merging methods.
-
-```python
-import torch
-from diffusers import StableDiffusionXLPipeline
-from scheduling_tcd import TCDScheduler 
-
-device = "cuda"
-base_model_id = "stabilityai/stable-diffusion-xl-base-1.0"
-tcd_lora_id = "h1t/TCD-SDXL-LoRA"
-styled_lora_id = "TheLastBen/Papercut_SDXL"
-
-pipe = StableDiffusionXLPipeline.from_pretrained(base_model_id, torch_dtype=torch.float16, variant="fp16").to(device)
-pipe.scheduler = TCDScheduler.from_config(pipe.scheduler.config)
-
-pipe.load_lora_weights(tcd_lora_id, adapter_name="tcd")
-pipe.load_lora_weights(styled_lora_id, adapter_name="style")
-pipe.set_adapters(["tcd", "style"], adapter_weights=[1.0, 1.0])
-
-prompt = "papercut of a winter mountain, snow"
-
-image = pipe(
-    prompt=prompt,
-    num_inference_steps=4,
-    guidance_scale=0,
-    eta=0.3, 
-    generator=torch.Generator(device=device).manual_seed(0),
-).images[0]
-```
-
-![](https://github.com/jabir-zheng/TCD/raw/main/assets/styled_lora.png)
-
-
-## Adapters
-
-TCD-LoRA is very versatile, and it can be combined with other adapter types like ControlNets, IP-Adapter, and AnimateDiff.
-
-<hfoptions id="adapters">
-<hfoption id="ControlNet">
-
-### Depth ControlNet
-
-```python
-import torch
-import numpy as np
-from PIL import Image
-from transformers import DPTFeatureExtractor, DPTForDepthEstimation
-from diffusers import ControlNetModel, StableDiffusionXLControlNetPipeline
-from diffusers.utils import load_image, make_image_grid
-from scheduling_tcd import TCDScheduler 
-
-device = "cuda"
-depth_estimator = DPTForDepthEstimation.from_pretrained("Intel/dpt-hybrid-midas").to(device)
-feature_extractor = DPTFeatureExtractor.from_pretrained("Intel/dpt-hybrid-midas")
-
-def get_depth_map(image):
-    image = feature_extractor(images=image, return_tensors="pt").pixel_values.to(device)
-    with torch.no_grad(), torch.autocast(device):
-        depth_map = depth_estimator(image).predicted_depth
-
-    depth_map = torch.nn.functional.interpolate(
-        depth_map.unsqueeze(1),
-        size=(1024, 1024),
-        mode="bicubic",
-        align_corners=False,
-    )
-    depth_min = torch.amin(depth_map, dim=[1, 2, 3], keepdim=True)
-    depth_max = torch.amax(depth_map, dim=[1, 2, 3], keepdim=True)
-    depth_map = (depth_map - depth_min) / (depth_max - depth_min)
-    image = torch.cat([depth_map] * 3, dim=1)
-
-    image = image.permute(0, 2, 3, 1).cpu().numpy()[0]
-    image = Image.fromarray((image * 255.0).clip(0, 255).astype(np.uint8))
-    return image
-
-base_model_id = "stabilityai/stable-diffusion-xl-base-1.0"
-controlnet_id = "diffusers/controlnet-depth-sdxl-1.0"
-tcd_lora_id = "h1t/TCD-SDXL-LoRA"
-
-controlnet = ControlNetModel.from_pretrained(
-    controlnet_id,
-    torch_dtype=torch.float16,
-    variant="fp16",
-).to(device)
-pipe = StableDiffusionXLControlNetPipeline.from_pretrained(
-    base_model_id,
-    controlnet=controlnet,
-    torch_dtype=torch.float16,
-    variant="fp16",
-).to(device)
-pipe.enable_model_cpu_offload()
-
-pipe.scheduler = TCDScheduler.from_config(pipe.scheduler.config)
-
-pipe.load_lora_weights(tcd_lora_id)
-pipe.fuse_lora()
-
-prompt = "stormtrooper lecture, photorealistic"
-
-image = load_image("https://huggingface.co/lllyasviel/sd-controlnet-depth/resolve/main/images/stormtrooper.png")
-depth_image = get_depth_map(image)
-
-controlnet_conditioning_scale = 0.5  # recommended for good generalization
-
-image = pipe(
-    prompt, 
-    image=depth_image, 
-    num_inference_steps=4, 
-    guidance_scale=0,
-    eta=0.3,
-    controlnet_conditioning_scale=controlnet_conditioning_scale,
-    generator=torch.Generator(device=device).manual_seed(0),
-).images[0]
-
-grid_image = make_image_grid([depth_image, image], rows=1, cols=2)
-```
-
-![](https://github.com/jabir-zheng/TCD/raw/main/assets/controlnet_depth_tcd.png)
-
-### Canny ControlNet
-```python
-import torch
-from diffusers import ControlNetModel, StableDiffusionXLControlNetPipeline
-from diffusers.utils import load_image, make_image_grid
-from scheduling_tcd import TCDScheduler 
-
-device = "cuda"
-base_model_id = "stabilityai/stable-diffusion-xl-base-1.0"
-controlnet_id = "diffusers/controlnet-canny-sdxl-1.0"
-tcd_lora_id = "h1t/TCD-SDXL-LoRA"
-
-controlnet = ControlNetModel.from_pretrained(
-    controlnet_id,
-    torch_dtype=torch.float16,
-    variant="fp16",
-).to(device)
-pipe = StableDiffusionXLControlNetPipeline.from_pretrained(
-    base_model_id,
-    controlnet=controlnet,
-    torch_dtype=torch.float16,
-    variant="fp16",
-).to(device)
-pipe.enable_model_cpu_offload()
-
-pipe.scheduler = TCDScheduler.from_config(pipe.scheduler.config)
-
-pipe.load_lora_weights(tcd_lora_id)
-pipe.fuse_lora()
-
-prompt = "ultrarealistic shot of a furry blue bird"
-
-canny_image = load_image("https://huggingface.co/datasets/hf-internal-testing/diffusers-images/resolve/main/sd_controlnet/bird_canny.png")
-
-controlnet_conditioning_scale = 0.5  # recommended for good generalization
-
-image = pipe(
-    prompt, 
-    image=canny_image, 
-    num_inference_steps=4, 
-    guidance_scale=0,
-    eta=0.3,
-    controlnet_conditioning_scale=controlnet_conditioning_scale,
-    generator=torch.Generator(device=device).manual_seed(0),
-).images[0]
-
-grid_image = make_image_grid([canny_image, image], rows=1, cols=2)
-```
-![](https://github.com/jabir-zheng/TCD/raw/main/assets/controlnet_canny_tcd.png)
-
-<Tip>
-The inference parameters in this example might not work for all examples, so we recommend you to try different values for `num_inference_steps`, `guidance_scale`, `controlnet_conditioning_scale` and `cross_attention_kwargs` parameters and choose the best one. 
-</Tip>
-
-</hfoption>
-<hfoption id="IP-Adapter">
-
-This example shows how to use the TCD-LoRA with the [IP-Adapter](https://github.com/tencent-ailab/IP-Adapter/tree/main) and SDXL.
-
-```python
-import torch
-from diffusers import StableDiffusionXLPipeline
-from diffusers.utils import load_image, make_image_grid
-
-from ip_adapter import IPAdapterXL
-from scheduling_tcd import TCDScheduler 
-
-device = "cuda"
-base_model_path = "stabilityai/stable-diffusion-xl-base-1.0"
-image_encoder_path = "sdxl_models/image_encoder"
-ip_ckpt = "sdxl_models/ip-adapter_sdxl.bin"
-tcd_lora_id = "h1t/TCD-SDXL-LoRA"
-
-pipe = StableDiffusionXLPipeline.from_pretrained(
-    base_model_path, 
-    torch_dtype=torch.float16, 
-    variant="fp16"
-)
-pipe.scheduler = TCDScheduler.from_config(pipe.scheduler.config)
-
-pipe.load_lora_weights(tcd_lora_id)
-pipe.fuse_lora()
-
-ip_model = IPAdapterXL(pipe, image_encoder_path, ip_ckpt, device)
-
-ref_image = load_image("https://raw.githubusercontent.com/tencent-ailab/IP-Adapter/main/assets/images/woman.png").resize((512, 512))
-
-prompt = "best quality, high quality, wearing sunglasses"
-
-image = ip_model.generate(
-    pil_image=ref_image, 
-    prompt=prompt,
-    scale=0.5,
-    num_samples=1, 
-    num_inference_steps=4, 
-    guidance_scale=0,
-    eta=0.3, 
-    seed=0,
-)[0]
-
-grid_image = make_image_grid([ref_image, image], rows=1, cols=2)
-```
-
-![](https://github.com/jabir-zheng/TCD/raw/main/assets/ip_adapter.png)
-
-
-
-</hfoption>
-<hfoption id="AnimateDiff">
-
-[`AnimateDiff`] allows animating images using Stable Diffusion models. TCD-LoRA can substantially accelerate the process without degrading image quality. The quality of animation with TCD-LoRA and AnimateDiff has a more lucid outcome.
-
-```python
-import torch
-from diffusers import MotionAdapter, AnimateDiffPipeline, DDIMScheduler
-from scheduling_tcd import TCDScheduler
-from diffusers.utils import export_to_gif
-
-adapter = MotionAdapter.from_pretrained("guoyww/animatediff-motion-adapter-v1-5")
-pipe = AnimateDiffPipeline.from_pretrained(
-    "frankjoshua/toonyou_beta6",
-    motion_adapter=adapter,
-).to("cuda")
-
-# set TCDScheduler
-pipe.scheduler = TCDScheduler.from_config(pipe.scheduler.config)
-
-# load TCD LoRA
-pipe.load_lora_weights("h1t/TCD-SD15-LoRA", adapter_name="tcd")
-pipe.load_lora_weights("guoyww/animatediff-motion-lora-zoom-in", weight_name="diffusion_pytorch_model.safetensors", adapter_name="motion-lora")
-
-pipe.set_adapters(["tcd", "motion-lora"], adapter_weights=[1.0, 1.2])
-
-prompt = "best quality, masterpiece, 1girl, looking at viewer, blurry background, upper body, contemporary, dress"
-generator = torch.manual_seed(0)
-frames = pipe(
-    prompt=prompt,
-    num_inference_steps=5,
-    guidance_scale=0,
-    cross_attention_kwargs={"scale": 1},
-    num_frames=24,
-    eta=0.3,
-    generator=generator
-).frames[0]
-export_to_gif(frames, "animation.gif")
-```
-
-![](https://github.com/jabir-zheng/TCD/raw/main/assets/animation_example.gif)
-
-</hfoption>
-</hfoptions>

docs/source/en/using-diffusers/ip_adapter.md

@@ -25,9 +25,6 @@ Let's take a look at how to use IP-Adapter's image prompting capabilities with t
 
 In all the following examples, you'll see the [`~loaders.IPAdapterMixin.set_ip_adapter_scale`] method. This method controls the amount of text or image conditioning to apply to the model. A value of `1.0` means the model is only conditioned on the image prompt. Lowering this value encourages the model to produce more diverse images, but they may not be as aligned with the image prompt. Typically, a value of `0.5` achieves a good balance between the two prompt types and produces good results.
 
-> [!TIP]
-> In the examples below, try adding `low_cpu_mem_usage=True` to the [`~loaders.IPAdapterMixin.load_ip_adapter`] method to speed up the loading time.
-
 <hfoptions id="tasks">
 <hfoption id="Text-to-image">
 
@@ -51,10 +48,10 @@ Create a text prompt and load an image prompt before passing them to the pipelin
 image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/ip_adapter_diner.png")
 generator = torch.Generator(device="cpu").manual_seed(0)
 images = pipeline(
-    prompt="a polar bear sitting in a chair drinking a milkshake",
+    prompt="a polar bear sitting in a chair drinking a milkshake", 
     ip_adapter_image=image,
     negative_prompt="deformed, ugly, wrong proportion, low res, bad anatomy, worst quality, low quality",
-    num_inference_steps=100,
+    num_inference_steps=100, 
     generator=generator,
 ).images
 images[0]
@@ -234,127 +231,8 @@ export_to_gif(frames, "gummy_bear.gif")
 </hfoption>
 </hfoptions>
 
-## Configure parameters
-
-There are a couple of IP-Adapter parameters that are useful to know about and can help you with your image generation tasks. These parameters can make your workflow more efficient or give you more control over image generation.
-
-### Image embeddings
-
-IP-Adapter enabled pipelines provide the `ip_adapter_image_embeds` parameter to accept precomputed image embeddings. This is particularly useful in scenarios where you need to run the IP-Adapter pipeline multiple times because you have more than one image. For example, [multi IP-Adapter](#multi-ip-adapter) is a specific use case where you provide multiple styling images to generate a specific image in a specific style. Loading and encoding multiple images each time you use the pipeline would be inefficient. Instead, you can precompute and save the image embeddings to disk (which can save a lot of space if you're using high-quality images) and load them when you need them.
-
 > [!TIP]
-> This parameter also gives you the flexibility to load embeddings from other sources. For example, ComfyUI image embeddings for IP-Adapters are compatible with Diffusers and should work ouf-of-the-box!
-
-Call the [`~StableDiffusionPipeline.prepare_ip_adapter_image_embeds`] method to encode and generate the image embeddings. Then you can save them to disk with `torch.save`.
-
-> [!TIP]
-> If you're using IP-Adapter with `ip_adapter_image_embedding` instead of `ip_adapter_image`', you can set `load_ip_adapter(image_encoder_folder=None,...)` because you don't need to load an encoder to generate the image embeddings.
-
-```py
-image_embeds = pipeline.prepare_ip_adapter_image_embeds(
-    ip_adapter_image=image,
-    ip_adapter_image_embeds=None,
-    device="cuda",
-    num_images_per_prompt=1,
-    do_classifier_free_guidance=True,
-)
-
-torch.save(image_embeds, "image_embeds.ipadpt")
-```
-
-Now load the image embeddings by passing them to the `ip_adapter_image_embeds` parameter.
-
-```py
-image_embeds = torch.load("image_embeds.ipadpt")
-images = pipeline(
-    prompt="a polar bear sitting in a chair drinking a milkshake",
-    ip_adapter_image_embeds=image_embeds,
-    negative_prompt="deformed, ugly, wrong proportion, low res, bad anatomy, worst quality, low quality",
-    num_inference_steps=100,
-    generator=generator,
-).images
-```
-
-### IP-Adapter masking
-
-Binary masks specify which portion of the output image should be assigned to an IP-Adapter. This is useful for composing more than one IP-Adapter image. For each input IP-Adapter image, you must provide a binary mask an an IP-Adapter.
-
-To start, preprocess the input IP-Adapter images with the [`~image_processor.IPAdapterMaskProcessor.preprocess()`] to generate their masks. For optimal results, provide the output height and width to [`~image_processor.IPAdapterMaskProcessor.preprocess()`]. This ensures masks with different aspect ratios are appropriately stretched. If the input masks already match the aspect ratio of the generated image, you don't have to set the `height` and `width`.
-
-```py
-from diffusers.image_processor import IPAdapterMaskProcessor
-
-mask1 = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/ip_mask_mask1.png")
-mask2 = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/ip_mask_mask2.png")
-
-output_height = 1024
-output_width = 1024
-
-processor = IPAdapterMaskProcessor()
-masks = processor.preprocess([mask1, mask2], height=output_height, width=output_width)
-```
-
-<div class="flex flex-row gap-4">
-  <div class="flex-1">
-    <img class="rounded-xl" src="https://huggingface.co/datasets/YiYiXu/testing-images/resolve/main/ip_mask_mask1.png"/>
-    <figcaption class="mt-2 text-center text-sm text-gray-500">mask one</figcaption>
-  </div>
-  <div class="flex-1">
-    <img class="rounded-xl" src="https://huggingface.co/datasets/YiYiXu/testing-images/resolve/main/ip_mask_mask2.png"/>
-    <figcaption class="mt-2 text-center text-sm text-gray-500">mask two</figcaption>
-  </div>
-</div>
-
-When there is more than one input IP-Adapter image, load them as a list to ensure each image is assigned to a different IP-Adapter. Each of the input IP-Adapter images here correspond to the masks generated above.
-
-```py
-face_image1 = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/ip_mask_girl1.png")
-face_image2 = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/ip_mask_girl2.png")
-
-ip_images = [[face_image1], [face_image2]]
-```
-
-<div class="flex flex-row gap-4">
-  <div class="flex-1">
-    <img class="rounded-xl" src="https://huggingface.co/datasets/YiYiXu/testing-images/resolve/main/ip_mask_girl1.png"/>
-    <figcaption class="mt-2 text-center text-sm text-gray-500">IP-Adapter image one</figcaption>
-  </div>
-  <div class="flex-1">
-    <img class="rounded-xl" src="https://huggingface.co/datasets/YiYiXu/testing-images/resolve/main/ip_mask_girl2.png"/>
-    <figcaption class="mt-2 text-center text-sm text-gray-500">IP-Adapter image two</figcaption>
-  </div>
-</div>
-
-Now pass the preprocessed masks to `cross_attention_kwargs` in the pipeline call.
-
-```py
-pipeline.load_ip_adapter("h94/IP-Adapter", subfolder="sdxl_models", weight_name=["ip-adapter-plus-face_sdxl_vit-h.safetensors"] * 2)
-pipeline.set_ip_adapter_scale([0.7] * 2)
-generator = torch.Generator(device="cpu").manual_seed(0)
-num_images = 1
-
-image = pipeline(
-    prompt="2 girls",
-    ip_adapter_image=ip_images,
-    negative_prompt="monochrome, lowres, bad anatomy, worst quality, low quality",
-    num_inference_steps=20,
-    num_images_per_prompt=num_images,
-    generator=generator,
-    cross_attention_kwargs={"ip_adapter_masks": masks}
-).images[0]
-image
-```
-
-<div class="flex flex-row gap-4">
-  <div class="flex-1">
-    <img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/ip_adapter_attention_mask_result_seed_0.png"/>
-    <figcaption class="mt-2 text-center text-sm text-gray-500">IP-Adapter masking applied</figcaption>
-  </div>
-  <div class="flex-1">
-    <img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/ip_adapter_no_attention_mask_result_seed_0.png"/>
-    <figcaption class="mt-2 text-center text-sm text-gray-500">no IP-Adapter masking applied</figcaption>
-  </div>
-</div>
+> While calling `load_ip_adapter()`, pass `low_cpu_mem_usage=True` to speed up the loading time.
 
 ## Specific use cases
 
@@ -362,12 +240,13 @@ IP-Adapter's image prompting and compatibility with other adapters and models ma
 
 ### Face model
 
-Generating accurate faces is challenging because they are complex and nuanced. Diffusers supports two IP-Adapter checkpoints specifically trained to generate faces from the [h94/IP-Adapter](https://huggingface.co/h94/IP-Adapter) repository:
+Generating accurate faces is challenging because they are complex and nuanced. Diffusers supports two IP-Adapter checkpoints specifically trained to generate faces:
 
 * [ip-adapter-full-face_sd15.safetensors](https://huggingface.co/h94/IP-Adapter/blob/main/models/ip-adapter-full-face_sd15.safetensors) is conditioned with images of cropped faces and removed backgrounds
 * [ip-adapter-plus-face_sd15.safetensors](https://huggingface.co/h94/IP-Adapter/blob/main/models/ip-adapter-plus-face_sd15.safetensors) uses patch embeddings and is conditioned with images of cropped faces
 
-Additionally, Diffusers supports all IP-Adapter checkpoints trained with face embeddings extracted by `insightface` face models. Supported models are from the [h94/IP-Adapter-FaceID](https://huggingface.co/h94/IP-Adapter-FaceID) repository.
+> [!TIP]
+> [IP-Adapter-FaceID](https://huggingface.co/h94/IP-Adapter-FaceID) is a face-specific IP-Adapter trained with face ID embeddings instead of CLIP image embeddings, allowing you to generate more consistent faces in different contexts and styles. Try out this popular [community pipeline](https://github.com/huggingface/diffusers/tree/main/examples/community#ip-adapter-face-id) and see how it compares to the other face IP-Adapters.
 
 For face models, use the [h94/IP-Adapter](https://huggingface.co/h94/IP-Adapter) checkpoint. It is also recommended to use [`DDIMScheduler`] or [`EulerDiscreteScheduler`] for face models.
 
@@ -391,7 +270,7 @@ generator = torch.Generator(device="cpu").manual_seed(26)
 image = pipeline(
     prompt="A photo of Einstein as a chef, wearing an apron, cooking in a French restaurant",
     ip_adapter_image=image,
-    negative_prompt="lowres, bad anatomy, worst quality, low quality",
+    negative_prompt="lowres, bad anatomy, worst quality, low quality", 
     num_inference_steps=100,
     generator=generator,
 ).images[0]
@@ -409,56 +288,6 @@ image
   </div>
 </div>
 
-To use IP-Adapter FaceID models, first extract face embeddings with `insightface`. Then pass the list of tensors to the pipeline as `ip_adapter_image_embeds`.
-
-```py
-import torch
-from diffusers import StableDiffusionPipeline, DDIMScheduler
-from diffusers.utils import load_image
-from insightface.app import FaceAnalysis
-
-pipeline = StableDiffusionPipeline.from_pretrained(
-    "runwayml/stable-diffusion-v1-5",
-    torch_dtype=torch.float16,
-).to("cuda")
-pipeline.scheduler = DDIMScheduler.from_config(pipeline.scheduler.config)
-pipeline.load_ip_adapter("h94/IP-Adapter-FaceID", subfolder=None, weight_name="ip-adapter-faceid_sd15.bin", image_encoder_folder=None)
-pipeline.set_ip_adapter_scale(0.6)
-
-image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/ip_mask_girl1.png")
-
-ref_images_embeds = []
-app = FaceAnalysis(name="buffalo_l", providers=['CUDAExecutionProvider', 'CPUExecutionProvider'])
-app.prepare(ctx_id=0, det_size=(640, 640))
-image = cv2.cvtColor(np.asarray(image), cv2.COLOR_BGR2RGB)
-faces = app.get(image)
-image = torch.from_numpy(faces[0].normed_embedding)
-ref_images_embeds.append(image.unsqueeze(0))
-ref_images_embeds = torch.stack(ref_images_embeds, dim=0).unsqueeze(0)
-neg_ref_images_embeds = torch.zeros_like(ref_images_embeds)
-id_embeds = torch.cat([neg_ref_images_embeds, ref_images_embeds]).to(dtype=torch.float16, device="cuda"))
-
-generator = torch.Generator(device="cpu").manual_seed(42)
-
-images = pipeline(
-    prompt="A photo of a girl",
-    ip_adapter_image_embeds=[id_embeds], 
-    negative_prompt="monochrome, lowres, bad anatomy, worst quality, low quality", 
-    num_inference_steps=20, num_images_per_prompt=1,
-    generator=generator
-).images
-```
-
-Both IP-Adapter FaceID Plus and Plus v2 models require CLIP image embeddings. You can prepare face embeddings as shown previously, then you can extract and pass CLIP embeddings to the hidden image projection layers.
-
-```py
-clip_embeds = pipeline.prepare_ip_adapter_image_embeds([ip_adapter_images], None, torch.device("cuda"), num_images, True)[0]
-
-pipeline.unet.encoder_hid_proj.image_projection_layers[0].clip_embeds = clip_embeds.to(dtype=torch.float16)
-pipeline.unet.encoder_hid_proj.image_projection_layers[0].shortcut = False # True if Plus v2
-```
-
-
 ### Multi IP-Adapter
 
 More than one IP-Adapter can be used at the same time to generate specific images in more diverse styles. For example, you can use IP-Adapter-Face to generate consistent faces and characters, and IP-Adapter Plus to generate those faces in a specific style.
@@ -475,7 +304,7 @@ from transformers import CLIPVisionModelWithProjection
 from diffusers.utils import load_image
 
 image_encoder = CLIPVisionModelWithProjection.from_pretrained(
-    "h94/IP-Adapter",
+    "h94/IP-Adapter", 
     subfolder="models/image_encoder",
     torch_dtype=torch.float16,
 )
@@ -494,8 +323,8 @@ pipeline = AutoPipelineForText2Image.from_pretrained(
 )
 pipeline.scheduler = DDIMScheduler.from_config(pipeline.scheduler.config)
 pipeline.load_ip_adapter(
-  "h94/IP-Adapter",
-  subfolder="sdxl_models",
+  "h94/IP-Adapter", 
+  subfolder="sdxl_models", 
   weight_name=["ip-adapter-plus_sdxl_vit-h.safetensors", "ip-adapter-plus-face_sdxl_vit-h.safetensors"]
 )
 pipeline.set_ip_adapter_scale([0.7, 0.3])
@@ -507,7 +336,7 @@ Load an image prompt and a folder containing images of a certain style you want
 ```py
 face_image = load_image("https://huggingface.co/datasets/YiYiXu/testing-images/resolve/main/women_input.png")
 style_folder = "https://huggingface.co/datasets/YiYiXu/testing-images/resolve/main/style_ziggy"
-style_images = [load_image(f"{style_folder}/img{i}.png") for i in range(10)]
+style_images =  [load_image(f"{style_folder}/img{i}.png") for i in range(10)]
 ```
 
 <div class="flex flex-row gap-4">
@@ -529,11 +358,10 @@ generator = torch.Generator(device="cpu").manual_seed(0)
 image = pipeline(
     prompt="wonderwoman",
     ip_adapter_image=[style_images, face_image],
-    negative_prompt="monochrome, lowres, bad anatomy, worst quality, low quality",
+    negative_prompt="monochrome, lowres, bad anatomy, worst quality, low quality", 
     num_inference_steps=50, num_images_per_prompt=1,
     generator=generator,
 ).images[0]
-image
 ```
 
 <div class="flex justify-center">
@@ -551,14 +379,14 @@ from diffusers import DiffusionPipeline, LCMScheduler
 import torch
 from diffusers.utils import load_image
 
-model_id = "sd-dreambooth-library/herge-style"
+model_id =  "sd-dreambooth-library/herge-style"
 lcm_lora_id = "latent-consistency/lcm-lora-sdv1-5"
 
 pipeline = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
 
 pipeline.load_ip_adapter("h94/IP-Adapter", subfolder="models", weight_name="ip-adapter_sd15.bin")
 pipeline.load_lora_weights(lcm_lora_id)
-pipeline.scheduler = LCMScheduler.from_config(pipeline.scheduler.config)
+pipeline.scheduler = LCMScheduler.from_config(pipe.scheduler.config)
 pipeline.enable_model_cpu_offload()
 ```
 
@@ -627,16 +455,96 @@ Pass the depth map and IP-Adapter image to the pipeline to generate an image.
 ```py
 generator = torch.Generator(device="cpu").manual_seed(33)
 image = pipeline(
-    prompt="best quality, high quality",
+    prompt="best quality, high quality", 
     image=depth_map,
     ip_adapter_image=ip_adapter_image,
-    negative_prompt="monochrome, lowres, bad anatomy, worst quality, low quality",
+    negative_prompt="monochrome, lowres, bad anatomy, worst quality, low quality", 
     num_inference_steps=50,
     generator=generator,
-).images[0]
+).image[0]
 image
 ```
 
 <div class="flex justify-center">
     <img src="https://huggingface.co/datasets/YiYiXu/testing-images/resolve/main/ipa-controlnet-out.png" />
 </div>
+
+### IP-Adapter masking
+
+Binary masks can be used to specify which portion of the output image should be assigned to an IP-Adapter.
+For each input IP-Adapter image, a binary mask and an IP-Adapter must be provided.
+
+Before passing the masks to the pipeline, it's essential to preprocess them using [`IPAdapterMaskProcessor.preprocess()`].
+
+> [!TIP]
+> For optimal results, provide the output height and width to [`IPAdapterMaskProcessor.preprocess()`]. This ensures that masks with differing aspect ratios are appropriately stretched. If the input masks already match the aspect ratio of the generated image, specifying height and width can be omitted.
+
+Here an example with two masks:
+
+```py
+from diffusers.image_processor import IPAdapterMaskProcessor
+
+mask1 = load_image("https://huggingface.co/datasets/YiYiXu/testing-images/resolve/main/ip_mask_mask1.png")
+mask2 = load_image("https://huggingface.co/datasets/YiYiXu/testing-images/resolve/main/ip_mask_mask2.png")
+
+output_height = 1024
+output_width = 1024
+
+processor = IPAdapterMaskProcessor()
+masks = processor.preprocess([mask1, mask2], height=output_height, width=output_width)
+```
+
+<div class="flex flex-row gap-4">
+  <div class="flex-1">
+    <img class="rounded-xl" src="https://huggingface.co/datasets/YiYiXu/testing-images/resolve/main/ip_mask_mask1.png"/>
+    <figcaption class="mt-2 text-center text-sm text-gray-500">mask one</figcaption>
+  </div>
+  <div class="flex-1">
+    <img class="rounded-xl" src="https://huggingface.co/datasets/YiYiXu/testing-images/resolve/main/ip_mask_mask2.png"/>
+    <figcaption class="mt-2 text-center text-sm text-gray-500">mask two</figcaption>
+  </div>
+</div>
+
+If you have more than one IP-Adapter image, load them into a list, ensuring each image is assigned to a different IP-Adapter.
+
+```py
+face_image1 = load_image("https://huggingface.co/datasets/YiYiXu/testing-images/resolve/main/ip_mask_girl1.png")
+face_image2 = load_image("https://huggingface.co/datasets/YiYiXu/testing-images/resolve/main/ip_mask_girl2.png")
+
+ip_images =[[image1], [image2]]
+
+```
+
+<div class="flex flex-row gap-4">
+  <div class="flex-1">
+    <img class="rounded-xl" src="https://huggingface.co/datasets/YiYiXu/testing-images/resolve/main/ip_mask_girl1.png"/>
+    <figcaption class="mt-2 text-center text-sm text-gray-500">ip adapter image one</figcaption>
+  </div>
+  <div class="flex-1">
+    <img class="rounded-xl" src="https://huggingface.co/datasets/YiYiXu/testing-images/resolve/main/ip_mask_girl2.png"/>
+    <figcaption class="mt-2 text-center text-sm text-gray-500">ip adapter image two</figcaption>
+  </div>
+</div>
+
+Pass preprocessed masks to the pipeline using `cross_attention_kwargs` as shown below:
+
+```py
+
+pipeline.load_ip_adapter("h94/IP-Adapter", subfolder="sdxl_models", weight_name=["ip-adapter-plus-face_sdxl_vit-h.safetensors"] * 2)
+pipeline.set_ip_adapter_scale([0.7] * 2)
+generator = torch.Generator(device="cpu").manual_seed(0)
+num_images=1
+
+image = pipeline(
+    prompt="2 girls",
+    ip_adapter_image=ip_images,
+    negative_prompt="monochrome, lowres, bad anatomy, worst quality, low quality", 
+    num_inference_steps=20, num_images_per_prompt=num_images, 
+    generator=generator, cross_attention_kwargs={"ip_adapter_masks": masks}
+).images[0]
+```
+
+<div class="flex justify-center">
+    <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/ip_adapter_attention_mask_result_seed_0.png" />
+   <figcaption class="mt-2 text-center text-sm text-gray-500">output image</figcaption>
+</div>

docs/source/en/using-diffusers/loading.md

@@ -10,394 +10,316 @@ an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express o
 specific language governing permissions and limitations under the License.
 -->
 
-# Load pipelines
+# Load pipelines, models, and schedulers
 
 [[open-in-colab]]
 
-Diffusion systems consist of multiple components like parameterized models and schedulers that interact in complex ways. That is why we designed the [`DiffusionPipeline`] to wrap the complexity of the entire diffusion system into an easy-to-use API. At the same time, the [`DiffusionPipeline`] is entirely customizable so you can modify each component to build a diffusion system for your use case.
+Having an easy way to use a diffusion system for inference is essential to 🧨 Diffusers. Diffusion systems often consist of multiple components like parameterized models, tokenizers, and schedulers that interact in complex ways. That is why we designed the [`DiffusionPipeline`] to wrap the complexity of the entire diffusion system into an easy-to-use API, while remaining flexible enough to be adapted for other use cases, such as loading each component individually as building blocks to assemble your own diffusion system.
+
+Everything you need for inference or training is accessible with the `from_pretrained()` method.
 
 This guide will show you how to load:
 
 - pipelines from the Hub and locally
 - different components into a pipeline
-- multiple pipelines without increasing memory usage
 - checkpoint variants such as different floating point types or non-exponential mean averaged (EMA) weights
+- models and schedulers
 
-## Load a pipeline
+## Diffusion Pipeline
 
-> [!TIP]
-> Skip to the [DiffusionPipeline explained](#diffusionpipeline-explained) section if you're interested in an explanation about how the [`DiffusionPipeline`] class works.
+<Tip>
 
-There are two ways to load a pipeline for a task:
+💡 Skip to the [DiffusionPipeline explained](#diffusionpipeline-explained) section if you are interested in learning in more detail about how the [`DiffusionPipeline`] class works.
 
-1. Load the generic [`DiffusionPipeline`] class and allow it to automatically detect the correct pipeline class from the checkpoint.
-2. Load a specific pipeline class for a specific task.
+</Tip>
 
-<hfoptions id="pipelines">
-<hfoption id="generic pipeline">
-
-The [`DiffusionPipeline`] class is a simple and generic way to load the latest trending diffusion model from the [Hub](https://huggingface.co/models?library=diffusers&sort=trending). It uses the [`~DiffusionPipeline.from_pretrained`] method to automatically detect the correct pipeline class for a task from the checkpoint, downloads and caches all the required configuration and weight files, and returns a pipeline ready for inference.
+The [`DiffusionPipeline`] class is the simplest and most generic way to load the latest trending diffusion model from the [Hub](https://huggingface.co/models?library=diffusers&sort=trending). The [`DiffusionPipeline.from_pretrained`] method automatically detects the correct pipeline class from the checkpoint, downloads, and caches all the required configuration and weight files, and returns a pipeline instance ready for inference.
 
 ```python
 from diffusers import DiffusionPipeline
 
-pipeline = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", use_safetensors=True)
+repo_id = "runwayml/stable-diffusion-v1-5"
+pipe = DiffusionPipeline.from_pretrained(repo_id, use_safetensors=True)
 ```
 
-This same checkpoint can also be used for an image-to-image task. The [`DiffusionPipeline`] class can handle any task as long as you provide the appropriate inputs. For example, for an image-to-image task, you need to pass an initial image to the pipeline.
-
-```py
-from diffusers import DiffusionPipeline
-
-pipeline = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", use_safetensors=True)
-
-init_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/img2img-init.png")
-prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
-image = pipeline("Astronaut in a jungle, cold color palette, muted colors, detailed, 8k", image=init_image).images[0]
-```
-
-</hfoption>
-<hfoption id="specific pipeline">
-
-Checkpoints can be loaded by their specific pipeline class if you already know it. For example, to load a Stable Diffusion model, use the [`StableDiffusionPipeline`] class.
+You can also load a checkpoint with its specific pipeline class. The example above loaded a Stable Diffusion model; to get the same result, use the [`StableDiffusionPipeline`] class:
 
 ```python
 from diffusers import StableDiffusionPipeline
 
-pipeline = StableDiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", use_safetensors=True)
+repo_id = "runwayml/stable-diffusion-v1-5"
+pipe = StableDiffusionPipeline.from_pretrained(repo_id, use_safetensors=True)
 ```
 
-This same checkpoint may also be used for another task like image-to-image. To differentiate what task you want to use the checkpoint for, you have to use the corresponding task-specific pipeline class. For example, to use the same checkpoint for image-to-image, use the [`StableDiffusionImg2ImgPipeline`] class.
+A checkpoint (such as [`CompVis/stable-diffusion-v1-4`](https://huggingface.co/CompVis/stable-diffusion-v1-4) or [`runwayml/stable-diffusion-v1-5`](https://huggingface.co/runwayml/stable-diffusion-v1-5)) may also be used for more than one task, like text-to-image or image-to-image. To differentiate what task you want to use the checkpoint for, you have to load it directly with its corresponding task-specific pipeline class:
 
-```py
+```python
 from diffusers import StableDiffusionImg2ImgPipeline
 
-pipeline = StableDiffusionImg2ImgPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", use_safetensors=True)
+repo_id = "runwayml/stable-diffusion-v1-5"
+pipe = StableDiffusionImg2ImgPipeline.from_pretrained(repo_id)
 ```
 
-</hfoption>
-</hfoptions>
-
-Use the Space below to gauge a pipeline's memory requirements before you download and load it to see if it runs on your hardware.
-
-<div class="block dark:hidden">
-	<iframe 
-        src="https://diffusers-compute-pipeline-size.hf.space?__theme=light"
-        width="850"
-        height="1600"
-    ></iframe>
-</div>
-<div class="hidden dark:block">
-    <iframe 
-        src="https://diffusers-compute-pipeline-size.hf.space?__theme=dark"
-        width="850"
-        height="1600"
-    ></iframe>
-</div>
-
 ### Local pipeline
 
-To load a pipeline locally, use [git-lfs](https://git-lfs.github.com/) to manually download a checkpoint to your local disk.
+To load a diffusion pipeline locally, use [`git-lfs`](https://git-lfs.github.com/) to manually download the checkpoint (in this case, [`runwayml/stable-diffusion-v1-5`](https://huggingface.co/runwayml/stable-diffusion-v1-5)) to your local disk. This creates a local folder, `./stable-diffusion-v1-5`, on your disk:
 
 ```bash
 git-lfs install
 git clone https://huggingface.co/runwayml/stable-diffusion-v1-5
 ```
 
-This creates a local folder, ./stable-diffusion-v1-5, on your disk and you should pass its path to [`~DiffusionPipeline.from_pretrained`].
+Then pass the local path to [`~DiffusionPipeline.from_pretrained`]:
 
 ```python
 from diffusers import DiffusionPipeline
 
-stable_diffusion = DiffusionPipeline.from_pretrained("./stable-diffusion-v1-5", use_safetensors=True)
+repo_id = "./stable-diffusion-v1-5"
+stable_diffusion = DiffusionPipeline.from_pretrained(repo_id, use_safetensors=True)
 ```
 
-The [`~DiffusionPipeline.from_pretrained`] method won't download files from the Hub when it detects a local path, but this also means it won't download and cache the latest changes to a checkpoint.
+The [`~DiffusionPipeline.from_pretrained`] method won't download any files from the Hub when it detects a local path, but this also means it won't download and cache the latest changes to a checkpoint.
 
-## Customize a pipeline
+### Swap components in a pipeline
 
-You can customize a pipeline by loading different components into it. This is important because you can:
+You can customize the default components of any pipeline with another compatible component. Customization is important because:
 
-- change to a scheduler with faster generation speed or higher generation quality depending on your needs (call the `scheduler.compatibles` method on your pipeline to see compatible schedulers)
-- change a default pipeline component to a newer and better performing one
+- Changing the scheduler is important for exploring the trade-off between generation speed and quality.
+- Different components of a model are typically trained independently and you can swap out a component with a better-performing one.
+- During finetuning, usually only some components - like the UNet or text encoder - are trained.
 
-For example, let's customize the default [stabilityai/stable-diffusion-xl-base-1.0](https://hf.co/stabilityai/stable-diffusion-xl-base-1.0) checkpoint with:
-
-- The [`HeunDiscreteScheduler`] to generate higher quality images at the expense of slower generation speed. You must pass the `subfolder="scheduler"` parameter in [`~HeunDiscreteScheduler.from_pretrained`] to load the scheduler configuration into the correct [subfolder](https://hf.co/stabilityai/stable-diffusion-xl-base-1.0/tree/main/scheduler) of the pipeline repository.
-- A more stable VAE that runs in fp16.
+To find out which schedulers are compatible for customization, you can use the `compatibles` method:
 
 ```py
-from diffusers import StableDiffusionXLPipeline, HeunDiscreteScheduler, AutoencoderKL
-import torch
+from diffusers import DiffusionPipeline
 
-scheduler = HeunDiscreteScheduler.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", subfolder="scheduler")
-vae = AutoencoderKL.from_pretrained("madebyollin/sdxl-vae-fp16-fix", torch_dtype=torch.float16, use_safetensors=True)
+repo_id = "runwayml/stable-diffusion-v1-5"
+stable_diffusion = DiffusionPipeline.from_pretrained(repo_id, use_safetensors=True)
+stable_diffusion.scheduler.compatibles
 ```
 
-Now pass the new scheduler and VAE to the [`StableDiffusionXLPipeline`].
+Let's use the [`SchedulerMixin.from_pretrained`] method to replace the default [`PNDMScheduler`] with a more performant scheduler, [`EulerDiscreteScheduler`]. The `subfolder="scheduler"` argument is required to load the scheduler configuration from the correct [subfolder](https://huggingface.co/runwayml/stable-diffusion-v1-5/tree/main/scheduler) of the pipeline repository.
 
-```py
-pipeline = StableDiffusionXLPipeline.from_pretrained(
-  "stabilityai/stable-diffusion-xl-base-1.0", 
-  scheduler=scheduler, 
-  vae=vae, 
-  torch_dtype=torch.float16, 
-  variant="fp16", 
-  use_safetensors=True
-).to("cuda")
-```
-
-## Reuse a pipeline
-
-When you load multiple pipelines that share the same model components, it makes sense to reuse the shared components instead of reloading everything into memory again, especially if your hardware is memory-constrained. For example:
-
-1. You generated an image with the [`StableDiffusionPipeline`] but you want to improve its quality with the [`StableDiffusionSAGPipeline`]. Both of these pipelines share the same pretrained model, so it'd be a waste of memory to load the same model twice.
-2. You want to add a model component, like a [`MotionAdapter`](../api/pipelines/animatediff#animatediffpipeline), to [`AnimateDiffPipeline`] which was instantiated from an existing [`StableDiffusionPipeline`]. Again, both pipelines share the same pretrained model, so it'd be a waste of memory to load an entirely new pipeline again.
-
-With the [`DiffusionPipeline.from_pipe`] API, you can switch between multiple pipelines to take advantage of their different features without increasing memory-usage. It is similar to turning on and off a feature in your pipeline. To switch between tasks, use the [`~DiffusionPipeline.from_pipe`] method with the [`AutoPipeline`](../api/pipelines/auto_pipeline) class, which automatically identifies the pipeline class based on the task (learn more in the [AutoPipeline](../tutorials/autopipeline) tutorial).
-
-Let's start with a [`StableDiffusionPipeline`] and then reuse the loaded model components to create a [`StableDiffusionSAGPipeline`] to increase generation quality. You'll use the [`StableDiffusionPipeline`] with an [IP-Adapter](./ip_adapter) to generate a bear eating pizza.
+Then you can pass the new [`EulerDiscreteScheduler`] instance to the `scheduler` argument in [`DiffusionPipeline`]:
 
 ```python
-from diffusers import DiffusionPipeline, StableDiffusionSAGPipeline
-import torch
-import gc
-from diffusers.utils import load_image
-from accelerate.utils import compute_module_sizes
+from diffusers import DiffusionPipeline, EulerDiscreteScheduler
 
-image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/load_neg_embed.png")
-
-pipe_sd = DiffusionPipeline.from_pretrained("SG161222/Realistic_Vision_V6.0_B1_noVAE", torch_dtype=torch.float16)
-pipe_sd.load_ip_adapter("h94/IP-Adapter", subfolder="models", weight_name="ip-adapter_sd15.bin")
-pipe_sd.set_ip_adapter_scale(0.6)
-pipe_sd.to("cuda")
-
-generator = torch.Generator(device="cpu").manual_seed(33)
-out_sd = pipe_sd(
-    prompt="bear eats pizza",
-    negative_prompt="wrong white balance, dark, sketches,worst quality,low quality", 
-    ip_adapter_image=image,
-    num_inference_steps=50,
-    generator=generator,
-).images[0]
-out_sd
+repo_id = "runwayml/stable-diffusion-v1-5"
+scheduler = EulerDiscreteScheduler.from_pretrained(repo_id, subfolder="scheduler")
+stable_diffusion = DiffusionPipeline.from_pretrained(repo_id, scheduler=scheduler, use_safetensors=True)
 ```
 
-<div class="flex justify-center">
-  <img class="rounded-xl" src="https://huggingface.co/datasets/YiYiXu/testing-images/resolve/main/from_pipe_out_sd_0.png"/>
-</div>
+### Safety checker
 
-For reference, you can check how much memory this process consumed.
-
-```python
-def bytes_to_giga_bytes(bytes):
-    return bytes / 1024 / 1024 / 1024
-print(f"Max memory allocated: {bytes_to_giga_bytes(torch.cuda.max_memory_allocated())} GB")
-"Max memory allocated: 4.406213283538818 GB"
-```
-
-Now, reuse the same pipeline components from [`StableDiffusionPipeline`] in [`StableDiffusionSAGPipeline`] with the [`~DiffusionPipeline.from_pipe`] method.
-
-> [!WARNING]
-> Some pipeline methods may not function properly on new pipelines created with [`~DiffusionPipeline.from_pipe`]. For instance, the [`~DiffusionPipeline.enable_model_cpu_offload`] method installs hooks on the model components based on a unique offloading sequence for each pipeline. If the models are executed in a different order in the new pipeline, the CPU offloading may not work correctly.
->
-> To ensure everything works as expected, we recommend re-applying a pipeline method on a new pipeline created with [`~DiffusionPipeline.from_pipe`].
-
-```python
-pipe_sag = StableDiffusionSAGPipeline.from_pipe(
-    pipe_sd
-)
-
-generator = torch.Generator(device="cpu").manual_seed(33)
-out_sag = pipe_sag(
-    prompt="bear eats pizza",
-    negative_prompt="wrong white balance, dark, sketches,worst quality,low quality",
-    ip_adapter_image=image,
-    num_inference_steps=50,
-    generator=generator,
-    guidance_scale=1.0,
-    sag_scale=0.75
-).images[0]
-out_sag
-```
-
-<div class="flex justify-center">
-  <img class="rounded-xl" src="https://huggingface.co/datasets/YiYiXu/testing-images/resolve/main/from_pipe_out_sag_1.png"/>
-</div>
-
-If you check the memory usage, you'll see it remains the same as before because [`StableDiffusionPipeline`] and [`StableDiffusionSAGPipeline`] are sharing the same pipeline components. This allows you to use them interchangeably without any additional memory overhead.
-
-```py
-print(f"Max memory allocated: {bytes_to_giga_bytes(torch.cuda.max_memory_allocated())} GB")
-"Max memory allocated: 4.406213283538818 GB"
-```
-
-Let's animate the image with the [`AnimateDiffPipeline`] and also add a [`MotionAdapter`] module to the pipeline. For the [`AnimateDiffPipeline`], you need to unload the IP-Adapter first and reload it *after* you've created your new pipeline (this only applies to the [`AnimateDiffPipeline`]).
-
-```py
-from diffusers import AnimateDiffPipeline, MotionAdapter, DDIMScheduler
-from diffusers.utils import export_to_gif
-
-pipe_sag.unload_ip_adapter()
-adapter = MotionAdapter.from_pretrained("guoyww/animatediff-motion-adapter-v1-5-2", torch_dtype=torch.float16)
-
-pipe_animate = AnimateDiffPipeline.from_pipe(pipe_sd, motion_adapter=adapter)
-pipe_animate.scheduler = DDIMScheduler.from_config(pipe_animate.scheduler.config, beta_schedule="linear")
-# load IP-Adapter and LoRA weights again
-pipe_animate.load_ip_adapter("h94/IP-Adapter", subfolder="models", weight_name="ip-adapter_sd15.bin")
-pipe_animate.load_lora_weights("guoyww/animatediff-motion-lora-zoom-out", adapter_name="zoom-out")
-pipe_animate.to("cuda")
-
-generator = torch.Generator(device="cpu").manual_seed(33)
-pipe_animate.set_adapters("zoom-out", adapter_weights=0.75)
-out = pipe_animate(
-    prompt="bear eats pizza",
-    num_frames=16,
-    num_inference_steps=50,
-    ip_adapter_image=image,
-    generator=generator,
-).frames[0]
-export_to_gif(out, "out_animate.gif")
-```
-
-<div class="flex justify-center">
-  <img class="rounded-xl" src="https://huggingface.co/datasets/YiYiXu/testing-images/resolve/main/from_pipe_out_animate_3.gif"/>
-</div>
-
-The [`AnimateDiffPipeline`] is more memory-intensive and consumes 15GB of memory (see the [Memory-usage of from_pipe](#memory-usage-of-from_pipe) section to learn what this means for your memory-usage).
-
-```py
-print(f"Max memory allocated: {bytes_to_giga_bytes(torch.cuda.max_memory_allocated())} GB")
-"Max memory allocated: 15.178664207458496 GB"
-```
-
-### Modify from_pipe components
-
-Pipelines loaded with [`~DiffusionPipeline.from_pipe`] can be customized with different model components or methods. However, whenever you modify the *state* of the model components, it affects all the other pipelines that share the same components. For example, if you call [`~diffusers.loaders.IPAdapterMixin.unload_ip_adapter`] on the [`StableDiffusionSAGPipeline`], you won't be able to use IP-Adapter with the [`StableDiffusionPipeline`] because it's been removed from their shared components.
-
-```py
-pipe.sag_unload_ip_adapter()
-
-generator = torch.Generator(device="cpu").manual_seed(33)
-out_sd = pipe_sd(
-    prompt="bear eats pizza",
-    negative_prompt="wrong white balance, dark, sketches,worst quality,low quality", 
-    ip_adapter_image=image,
-    num_inference_steps=50,
-    generator=generator,
-).images[0]
-"AttributeError: 'NoneType' object has no attribute 'image_projection_layers'"
-```
-
-### Memory usage of from_pipe
-
-The memory requirement of loading multiple pipelines with [`~DiffusionPipeline.from_pipe`] is determined by the pipeline with the highest memory-usage regardless of the number of pipelines you create.
-
-| Pipeline | Memory usage (GB) |
-|---|---|
-| StableDiffusionPipeline | 4.400 |
-| StableDiffusionSAGPipeline | 4.400 |
-| AnimateDiffPipeline | 15.178 |
-
-The [`AnimateDiffPipeline`] has the highest memory requirement, so the *total memory-usage* is based only on the [`AnimateDiffPipeline`]. Your memory-usage will not increase if you create additional pipelines as long as their memory requirements doesn't exceed that of the [`AnimateDiffPipeline`]. Each pipeline can be used interchangeably without any additional memory overhead.
-
-## Safety checker
-
-Diffusers implements a [safety checker](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/stable_diffusion/safety_checker.py) for Stable Diffusion models which can generate harmful content. The safety checker screens the generated output against known hardcoded not-safe-for-work (NSFW) content. If for whatever reason you'd like to disable the safety checker, pass `safety_checker=None` to the [`~DiffusionPipeline.from_pretrained`] method.
+Diffusion models like Stable Diffusion can generate harmful content, which is why 🧨 Diffusers has a [safety checker](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/stable_diffusion/safety_checker.py) to check generated outputs against known hardcoded NSFW content. If you'd like to disable the safety checker for whatever reason, pass `None` to the `safety_checker` argument:
 
 ```python
 from diffusers import DiffusionPipeline
 
-pipeline = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", safety_checker=None, use_safetensors=True)
+repo_id = "runwayml/stable-diffusion-v1-5"
+stable_diffusion = DiffusionPipeline.from_pretrained(repo_id, safety_checker=None, use_safetensors=True)
 """
 You have disabled the safety checker for <class 'diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline'> by passing `safety_checker=None`. Ensure that you abide by the conditions of the Stable Diffusion license and do not expose unfiltered results in services or applications open to the public. Both the diffusers team and Hugging Face strongly recommend keeping the safety filter enabled in all public-facing circumstances, disabling it only for use cases that involve analyzing network behavior or auditing its results. For more information, please have a look at https://github.com/huggingface/diffusers/pull/254 .
 """
 ```
 
+### Reuse components across pipelines
+
+You can also reuse the same components in multiple pipelines to avoid loading the weights into RAM twice. Use the [`~DiffusionPipeline.components`] method to save the components:
+
+```python
+from diffusers import StableDiffusionPipeline, StableDiffusionImg2ImgPipeline
+
+model_id = "runwayml/stable-diffusion-v1-5"
+stable_diffusion_txt2img = StableDiffusionPipeline.from_pretrained(model_id, use_safetensors=True)
+
+components = stable_diffusion_txt2img.components
+```
+
+Then you can pass the `components` to another pipeline without reloading the weights into RAM:
+
+```py
+stable_diffusion_img2img = StableDiffusionImg2ImgPipeline(**components)
+```
+
+You can also pass the components individually to the pipeline if you want more flexibility over which components to reuse or disable. For example, to reuse the same components in the text-to-image pipeline, except for the safety checker and feature extractor, in the image-to-image pipeline:
+
+```py
+from diffusers import StableDiffusionPipeline, StableDiffusionImg2ImgPipeline
+
+model_id = "runwayml/stable-diffusion-v1-5"
+stable_diffusion_txt2img = StableDiffusionPipeline.from_pretrained(model_id, use_safetensors=True)
+stable_diffusion_img2img = StableDiffusionImg2ImgPipeline(
+    vae=stable_diffusion_txt2img.vae,
+    text_encoder=stable_diffusion_txt2img.text_encoder,
+    tokenizer=stable_diffusion_txt2img.tokenizer,
+    unet=stable_diffusion_txt2img.unet,
+    scheduler=stable_diffusion_txt2img.scheduler,
+    safety_checker=None,
+    feature_extractor=None,
+    requires_safety_checker=False,
+)
+```
+
 ## Checkpoint variants
 
 A checkpoint variant is usually a checkpoint whose weights are:
 
-- Stored in a different floating point type, such as [torch.float16](https://pytorch.org/docs/stable/tensors.html#data-types), because it only requires half the bandwidth and storage to download. You can't use this variant if you're continuing training or using a CPU.
-- Non-exponential mean averaged (EMA) weights which shouldn't be used for inference. You should use this variant to continue finetuning a model.
+- Stored in a different floating point type for lower precision and lower storage, such as [`torch.float16`](https://pytorch.org/docs/stable/tensors.html#data-types), because it only requires half the bandwidth and storage to download. You can't use this variant if you're continuing training or using a CPU.
+- Non-exponential mean averaged (EMA) weights, which shouldn't be used for inference. You should use these to continue fine-tuning a model.
 
-> [!TIP]
-> When the checkpoints have identical model structures, but they were trained on different datasets and with a different training setup, they should be stored in separate repositories. For example, [stabilityai/stable-diffusion-2](https://hf.co/stabilityai/stable-diffusion-2) and [stabilityai/stable-diffusion-2-1](https://hf.co/stabilityai/stable-diffusion-2-1) are stored in separate repositories.
+<Tip>
 
-Otherwise, a variant is **identical** to the original checkpoint. They have exactly the same serialization format (like [safetensors](./using_safetensors)), model structure, and their weights have identical tensor shapes.
+💡 When the checkpoints have identical model structures, but they were trained on different datasets and with a different training setup, they should be stored in separate repositories instead of variations (for example, [`stable-diffusion-v1-4`] and [`stable-diffusion-v1-5`]).
 
-| **checkpoint type** | **weight name**                             | **argument for loading weights** |
-|---------------------|---------------------------------------------|----------------------------------|
-| original            | diffusion_pytorch_model.safetensors         |                                  |
-| floating point      | diffusion_pytorch_model.fp16.safetensors    | `variant`, `torch_dtype`         |
-| non-EMA             | diffusion_pytorch_model.non_ema.safetensors | `variant`                        |
+</Tip>
 
-There are two important arguments for loading variants:
+Otherwise, a variant is **identical** to the original checkpoint. They have exactly the same serialization format (like [Safetensors](./using_safetensors)), model structure, and weights that have identical tensor shapes.
 
-- `torch_dtype` specifies the floating point precision of the loaded checkpoint. For example, if you want to save bandwidth by loading a fp16 variant, you should set `variant="fp16"` and `torch_dtype=torch.float16` to *convert the weights* to fp16. Otherwise, the fp16 weights are converted to the default fp32 precision.
+| **checkpoint type** | **weight name**                     | **argument for loading weights** |
+|---------------------|-------------------------------------|----------------------------------|
+| original            | diffusion_pytorch_model.bin         |                                  |
+| floating point      | diffusion_pytorch_model.fp16.bin    | `variant`, `torch_dtype`         |
+| non-EMA             | diffusion_pytorch_model.non_ema.bin | `variant`                        |
 
-  If you only set `torch_dtype=torch.float16`, the default fp32 weights are downloaded first and then converted to fp16.
+There are two important arguments to know for loading variants:
 
-- `variant` specifies which files should be loaded from the repository. For example, if you want to load a non-EMA variant of a UNet from [runwayml/stable-diffusion-v1-5](https://hf.co/runwayml/stable-diffusion-v1-5/tree/main/unet), set `variant="non_ema"` to download the `non_ema` file.
+- `torch_dtype` defines the floating point precision of the loaded checkpoints. For example, if you want to save bandwidth by loading a `fp16` variant, you should specify `torch_dtype=torch.float16` to *convert the weights* to `fp16`. Otherwise, the `fp16` weights are converted to the default `fp32` precision. You can also load the original checkpoint without defining the `variant` argument, and convert it to `fp16` with `torch_dtype=torch.float16`. In this case, the default `fp32` weights are downloaded first, and then they're converted to `fp16` after loading.
 
-<hfoptions id="variants">
-<hfoption id="fp16">
+- `variant` defines which files should be loaded from the repository. For example, if you want to load a `non_ema` variant from the [`diffusers/stable-diffusion-variants`](https://huggingface.co/diffusers/stable-diffusion-variants/tree/main/unet) repository, you should specify `variant="non_ema"` to download the `non_ema` files.
 
-```py
+```python
 from diffusers import DiffusionPipeline
 import torch
 
-pipeline = DiffusionPipeline.from_pretrained(
+# load fp16 variant
+stable_diffusion = DiffusionPipeline.from_pretrained(
     "runwayml/stable-diffusion-v1-5", variant="fp16", torch_dtype=torch.float16, use_safetensors=True
 )
-```
-
-</hfoption>
-<hfoption id="non-EMA">
-
-```py
-pipeline = DiffusionPipeline.from_pretrained(
+# load non_ema variant
+stable_diffusion = DiffusionPipeline.from_pretrained(
     "runwayml/stable-diffusion-v1-5", variant="non_ema", use_safetensors=True
 )
 ```
 
-</hfoption>
-</hfoptions>
-
-Use the `variant` parameter in the [`DiffusionPipeline.save_pretrained`] method to save a checkpoint as a different floating point type or as a non-EMA variant. You should try save a variant to the same folder as the original checkpoint, so you have the option of loading both from the same folder.
-
-<hfoptions id="save">
-<hfoption id="fp16">
+To save a checkpoint stored in a different floating-point type or as a non-EMA variant, use the [`DiffusionPipeline.save_pretrained`] method and specify the `variant` argument. You should try and save a variant to the same folder as the original checkpoint, so you can load both from the same folder:
 
 ```python
 from diffusers import DiffusionPipeline
 
-pipeline.save_pretrained("runwayml/stable-diffusion-v1-5", variant="fp16")
+# save as fp16 variant
+stable_diffusion.save_pretrained("runwayml/stable-diffusion-v1-5", variant="fp16")
+# save as non-ema variant
+stable_diffusion.save_pretrained("runwayml/stable-diffusion-v1-5", variant="non_ema")
 ```
 
-</hfoption>
-<hfoption id="non_ema">
-
-```py
-pipeline.save_pretrained("runwayml/stable-diffusion-v1-5", variant="non_ema")
-```
-
-</hfoption>
-</hfoptions>
-
-If you don't save the variant to an existing folder, you must specify the `variant` argument otherwise it'll throw an `Exception` because it can't find the original checkpoint.
+If you don't save the variant to an existing folder, you must specify the `variant` argument otherwise it'll throw an `Exception` because it can't find the original checkpoint:
 
 ```python
 # 👎 this won't work
-pipeline = DiffusionPipeline.from_pretrained(
+stable_diffusion = DiffusionPipeline.from_pretrained(
     "./stable-diffusion-v1-5", torch_dtype=torch.float16, use_safetensors=True
 )
 # 👍 this works
-pipeline = DiffusionPipeline.from_pretrained(
+stable_diffusion = DiffusionPipeline.from_pretrained(
     "./stable-diffusion-v1-5", variant="fp16", torch_dtype=torch.float16, use_safetensors=True
 )
 ```
 
+<!--
+TODO(Patrick) - Make sure to uncomment this part as soon as things are deprecated.
+
+#### Using `revision` to load pipeline variants is deprecated
+
+Previously the `revision` argument of [`DiffusionPipeline.from_pretrained`] was heavily used to
+load model variants, e.g.:
+
+```python
+from diffusers import DiffusionPipeline
+
+pipe = DiffusionPipeline.from_pretrained("CompVis/stable-diffusion-v1-4", revision="fp16", use_safetensors=True)
+```
+
+However, this behavior is now deprecated since the "revision" argument should (just as it's done in GitHub) better be used to load model checkpoints from a specific commit or branch in development.
+
+The above example is therefore deprecated and won't be supported anymore for `diffusers >= 1.0.0`.
+
+<Tip warning={true}>
+
+If you load diffusers pipelines or models with `revision="fp16"` or `revision="non_ema"`,
+please make sure to update the code and use `variant="fp16"` or `variation="non_ema"` respectively
+instead.
+
+</Tip>
+-->
+
+## Models
+
+Models are loaded from the [`ModelMixin.from_pretrained`] method, which downloads and caches the latest version of the model weights and configurations. If the latest files are available in the local cache, [`~ModelMixin.from_pretrained`] reuses files in the cache instead of re-downloading them.
+
+Models can be loaded from a subfolder with the `subfolder` argument. For example, the model weights for `runwayml/stable-diffusion-v1-5` are stored in the [`unet`](https://huggingface.co/runwayml/stable-diffusion-v1-5/tree/main/unet) subfolder:
+
+```python
+from diffusers import UNet2DConditionModel
+
+repo_id = "runwayml/stable-diffusion-v1-5"
+model = UNet2DConditionModel.from_pretrained(repo_id, subfolder="unet", use_safetensors=True)
+```
+
+Or directly from a repository's [directory](https://huggingface.co/google/ddpm-cifar10-32/tree/main):
+
+```python
+from diffusers import UNet2DModel
+
+repo_id = "google/ddpm-cifar10-32"
+model = UNet2DModel.from_pretrained(repo_id, use_safetensors=True)
+```
+
+You can also load and save model variants by specifying the `variant` argument in [`ModelMixin.from_pretrained`] and [`ModelMixin.save_pretrained`]:
+
+```python
+from diffusers import UNet2DConditionModel
+
+model = UNet2DConditionModel.from_pretrained(
+    "runwayml/stable-diffusion-v1-5", subfolder="unet", variant="non_ema", use_safetensors=True
+)
+model.save_pretrained("./local-unet", variant="non_ema")
+```
+
+## Schedulers
+
+Schedulers are loaded from the [`SchedulerMixin.from_pretrained`] method, and unlike models, schedulers are **not parameterized** or **trained**; they are defined by a configuration file.
+
+Loading schedulers does not consume any significant amount of memory and the same configuration file can be used for a variety of different schedulers.
+For example, the following schedulers are compatible with [`StableDiffusionPipeline`], which means you can load the same scheduler configuration file in any of these classes:
+
+```python
+from diffusers import StableDiffusionPipeline
+from diffusers import (
+    DDPMScheduler,
+    DDIMScheduler,
+    PNDMScheduler,
+    LMSDiscreteScheduler,
+    EulerAncestralDiscreteScheduler,
+    EulerDiscreteScheduler,
+    DPMSolverMultistepScheduler,
+)
+
+repo_id = "runwayml/stable-diffusion-v1-5"
+
+ddpm = DDPMScheduler.from_pretrained(repo_id, subfolder="scheduler")
+ddim = DDIMScheduler.from_pretrained(repo_id, subfolder="scheduler")
+pndm = PNDMScheduler.from_pretrained(repo_id, subfolder="scheduler")
+lms = LMSDiscreteScheduler.from_pretrained(repo_id, subfolder="scheduler")
+euler_anc = EulerAncestralDiscreteScheduler.from_pretrained(repo_id, subfolder="scheduler")
+euler = EulerDiscreteScheduler.from_pretrained(repo_id, subfolder="scheduler")
+dpm = DPMSolverMultistepScheduler.from_pretrained(repo_id, subfolder="scheduler")
+
+# replace `dpm` with any of `ddpm`, `ddim`, `pndm`, `lms`, `euler_anc`, `euler`
+pipeline = StableDiffusionPipeline.from_pretrained(repo_id, scheduler=dpm, use_safetensors=True)
+```
+
 ## DiffusionPipeline explained
 
 As a class method, [`DiffusionPipeline.from_pretrained`] is responsible for two things:

docs/source/en/using-diffusers/loading_adapters.md

@@ -103,7 +103,7 @@ image
 
 <Tip>
 
-LoRA is a very general training technique that can be used with other training methods. For example, it is common to train a model with DreamBooth and LoRA. It is also increasingly common to load and merge multiple LoRAs to create new and unique images. You can learn more about it in the in-depth [Merge LoRAs](merge_loras) guide since merging is outside the scope of this loading guide.
+LoRA is a very general training technique that can be used with other training methods. For example, it is common to train a model with DreamBooth and LoRA.
 
 </Tip>
 
@@ -153,51 +153,113 @@ image
     <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/load_attn_proc.png" />
 </div>
 
+<Tip>
+
+For both [`~loaders.LoraLoaderMixin.load_lora_weights`] and [`~loaders.UNet2DConditionLoadersMixin.load_attn_procs`], you can pass the `cross_attention_kwargs={"scale": 0.5}` parameter to adjust how much of the LoRA weights to use. A value of `0` is the same as only using the base model weights, and a value of `1` is equivalent to using the fully finetuned LoRA.
+
+</Tip>
+
 To unload the LoRA weights, use the [`~loaders.LoraLoaderMixin.unload_lora_weights`] method to discard the LoRA weights and restore the model to its original weights:
 
 ```py
 pipeline.unload_lora_weights()
 ```
 
-### Adjust LoRA weight scale
+### Load multiple LoRAs
 
-For both [`~loaders.LoraLoaderMixin.load_lora_weights`] and [`~loaders.UNet2DConditionLoadersMixin.load_attn_procs`], you can pass the `cross_attention_kwargs={"scale": 0.5}` parameter to adjust how much of the LoRA weights to use. A value of `0` is the same as only using the base model weights, and a value of `1` is equivalent to using the fully finetuned LoRA.
+It can be fun to use multiple LoRAs together to create something entirely new and unique. The [`~loaders.LoraLoaderMixin.fuse_lora`] method allows you to fuse the LoRA weights with the original weights of the underlying model.
 
-For more granular control on the amount of LoRA weights used per layer, you can use [`~loaders.LoraLoaderMixin.set_adapters`] and pass a dictionary specifying by how much to scale the weights in each layer by.
-```python
-pipe = ... # create pipeline
-pipe.load_lora_weights(..., adapter_name="my_adapter") 
-scales = {
-    "text_encoder": 0.5,
-    "text_encoder_2": 0.5,  # only usable if pipe has a 2nd text encoder
-    "unet": {
-        "down": 0.9,  # all transformers in the down-part will use scale 0.9
-        # "mid"  # in this example "mid" is not given, therefore all transformers in the mid part will use the default scale 1.0
-        "up": {
-            "block_0": 0.6,  # all 3 transformers in the 0th block in the up-part will use scale 0.6
-            "block_1": [0.4, 0.8, 1.0],  # the 3 transformers in the 1st block in the up-part will use scales 0.4, 0.8 and 1.0 respectively
-        }
-    }
-}
-pipe.set_adapters("my_adapter", scales)
+<Tip>
+
+Fusing the weights can lead to a speedup in inference latency because you don't need to separately load the base model and LoRA! You can save your fused pipeline with [`~DiffusionPipeline.save_pretrained`] to avoid loading and fusing the weights every time you want to use the model.
+
+</Tip>
+
+Load an initial model:
+
+```py
+from diffusers import StableDiffusionXLPipeline, AutoencoderKL
+import torch
+
+vae = AutoencoderKL.from_pretrained("madebyollin/sdxl-vae-fp16-fix", torch_dtype=torch.float16)
+pipeline = StableDiffusionXLPipeline.from_pretrained(
+    "stabilityai/stable-diffusion-xl-base-1.0",
+    vae=vae,
+    torch_dtype=torch.float16,
+).to("cuda")
 ```
 
-This also works with multiple adapters - see [this guide](https://huggingface.co/docs/diffusers/tutorials/using_peft_for_inference#customize-adapters-strength) for how to do it.
+Next, load the LoRA checkpoint and fuse it with the original weights. The `lora_scale` parameter controls how much to scale the output by with the LoRA weights. It is important to make the `lora_scale` adjustments in the [`~loaders.LoraLoaderMixin.fuse_lora`] method because it won't work if you try to pass `scale` to the `cross_attention_kwargs` in the pipeline.
+
+If you need to reset the original model weights for any reason (use a different `lora_scale`), you should use the [`~loaders.LoraLoaderMixin.unfuse_lora`] method.
+
+```py
+pipeline.load_lora_weights("ostris/ikea-instructions-lora-sdxl")
+pipeline.fuse_lora(lora_scale=0.7)
+
+# to unfuse the LoRA weights
+pipeline.unfuse_lora()
+```
+
+Then fuse this pipeline with the next set of LoRA weights:
+
+```py
+pipeline.load_lora_weights("ostris/super-cereal-sdxl-lora")
+pipeline.fuse_lora(lora_scale=0.7)
+```
 
 <Tip warning={true}>
 
-Currently, [`~loaders.LoraLoaderMixin.set_adapters`] only supports scaling attention weights. If a LoRA has other parts (e.g., resnets or down-/upsamplers), they will keep a scale of 1.0.
+You can't unfuse multiple LoRA checkpoints, so if you need to reset the model to its original weights, you'll need to reload it.
 
 </Tip>
 
+Now you can generate an image that uses the weights from both LoRAs:
+
+```py
+prompt = "A cute brown bear eating a slice of pizza, stunning color scheme, masterpiece, illustration"
+image = pipeline(prompt).images[0]
+image
+```
+
+### 🤗 PEFT
+
+<Tip>
+
+Read the [Inference with 🤗 PEFT](../tutorials/using_peft_for_inference) tutorial to learn more about its integration with 🤗 Diffusers and how you can easily work with and juggle multiple adapters. You'll need to install 🤗 Diffusers and PEFT from source to run the example in this section.
+
+</Tip>
+
+Another way you can load and use multiple LoRAs is to specify the `adapter_name` parameter in [`~loaders.LoraLoaderMixin.load_lora_weights`]. This method takes advantage of the 🤗 PEFT integration. For example, load and name both LoRA weights:
+
+```py
+from diffusers import DiffusionPipeline
+import torch
+
+pipeline = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=torch.float16).to("cuda")
+pipeline.load_lora_weights("ostris/ikea-instructions-lora-sdxl", weight_name="ikea_instructions_xl_v1_5.safetensors", adapter_name="ikea")
+pipeline.load_lora_weights("ostris/super-cereal-sdxl-lora", weight_name="cereal_box_sdxl_v1.safetensors", adapter_name="cereal")
+```
+
+Now use the [`~loaders.UNet2DConditionLoadersMixin.set_adapters`] to activate both LoRAs, and you can configure how much weight each LoRA should have on the output:
+
+```py
+pipeline.set_adapters(["ikea", "cereal"], adapter_weights=[0.7, 0.5])
+```
+
+Then, generate an image:
+
+```py
+prompt = "A cute brown bear eating a slice of pizza, stunning color scheme, masterpiece, illustration"
+image = pipeline(prompt, num_inference_steps=30, cross_attention_kwargs={"scale": 1.0}).images[0]
+image
+```
+
 ### Kohya and TheLastBen
 
 Other popular LoRA trainers from the community include those by [Kohya](https://github.com/kohya-ss/sd-scripts/) and [TheLastBen](https://github.com/TheLastBen/fast-stable-diffusion). These trainers create different LoRA checkpoints than those trained by 🤗 Diffusers, but they can still be loaded in the same way.
 
-<hfoptions id="other-trainers">
-<hfoption id="Kohya">
-
-To load a Kohya LoRA, let's download the [Blueprintify SD XL 1.0](https://civitai.com/models/150986/blueprintify-sd-xl-10) checkpoint from [Civitai](https://civitai.com/) as an example:
+Let's download the [Blueprintify SD XL 1.0](https://civitai.com/models/150986/blueprintify-sd-xl-10) checkpoint from [Civitai](https://civitai.com/):
 
 ```sh
 !wget https://civitai.com/api/download/models/168776 -O blueprintify-sd-xl-10.safetensors
@@ -231,9 +293,6 @@ Some limitations of using Kohya LoRAs with 🤗 Diffusers include:
 
 </Tip>
 
-</hfoption>
-<hfoption id="TheLastBen">
-
 Loading a checkpoint from TheLastBen is very similar. For example, to load the [TheLastBen/William_Eggleston_Style_SDXL](https://huggingface.co/TheLastBen/William_Eggleston_Style_SDXL) checkpoint:
 
 ```py
@@ -249,9 +308,6 @@ image = pipeline(prompt=prompt).images[0]
 image
 ```
 
-</hfoption>
-</hfoptions>
-
 ## IP-Adapter
 
 [IP-Adapter](https://ip-adapter.github.io/) is a lightweight adapter that enables image prompting for any diffusion model. This adapter works by decoupling the cross-attention layers of the image and text features. All the other model components are frozen and only the embedded image features in the UNet are trained. As a result, IP-Adapter files are typically only ~100MBs.
@@ -284,9 +340,9 @@ Once loaded, you can use the pipeline with an image and text prompt to guide the
 image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/load_neg_embed.png")
 generator = torch.Generator(device="cpu").manual_seed(33)
 images = pipeline(
-    prompt='best quality, high quality, wearing sunglasses',
+    prompt='best quality, high quality, wearing sunglasses', 
     ip_adapter_image=image,
-    negative_prompt="monochrome, lowres, bad anatomy, worst quality, low quality",
+    negative_prompt="monochrome, lowres, bad anatomy, worst quality, low quality", 
     num_inference_steps=50,
     generator=generator,
 ).images[0]
@@ -299,13 +355,11 @@ images
 
 ### IP-Adapter Plus
 
-IP-Adapter relies on an image encoder to generate image features. If the IP-Adapter repository contains an `image_encoder` subfolder, the image encoder is automatically loaded and registered to the pipeline. Otherwise, you'll need to explicitly load the image encoder with a [`~transformers.CLIPVisionModelWithProjection`] model and pass it to the pipeline.
+IP-Adapter relies on an image encoder to generate image features. If the IP-Adapter repository contains a `image_encoder` subfolder, the image encoder is automatically loaded and registed to the pipeline. Otherwise, you'll need to explicitly load the image encoder with a [`~transformers.CLIPVisionModelWithProjection`] model and pass it to the pipeline.
 
 This is the case for *IP-Adapter Plus* checkpoints which use the ViT-H image encoder.
 
 ```py
-from transformers import CLIPVisionModelWithProjection
-
 image_encoder = CLIPVisionModelWithProjection.from_pretrained(
     "h94/IP-Adapter",
     subfolder="models/image_encoder",
@@ -320,40 +374,3 @@ pipeline = AutoPipelineForText2Image.from_pretrained(
 
 pipeline.load_ip_adapter("h94/IP-Adapter", subfolder="sdxl_models", weight_name="ip-adapter-plus_sdxl_vit-h.safetensors")
 ```
-
-### IP-Adapter Face ID models
-
-The IP-Adapter FaceID models are experimental IP Adapters that use image embeddings generated by `insightface` instead of CLIP image embeddings. Some of these models also use LoRA to improve ID consistency.
-You need to install `insightface` and all its requirements to use these models.
-
-<Tip warning={true}>
-As InsightFace pretrained models are available for non-commercial research purposes, IP-Adapter-FaceID models are released exclusively for research purposes and are not intended for commercial use.
-</Tip>
-
-```py
-pipeline = AutoPipelineForText2Image.from_pretrained(
-    "stabilityai/stable-diffusion-xl-base-1.0",
-    torch_dtype=torch.float16
-).to("cuda")
-
-pipeline.load_ip_adapter("h94/IP-Adapter-FaceID", subfolder=None, weight_name="ip-adapter-faceid_sdxl.bin", image_encoder_folder=None)
-```
-
-If you want to use one of the two IP-Adapter FaceID Plus models, you must also load the CLIP image encoder, as this models use both `insightface` and CLIP image embeddings to achieve better photorealism.
-
-```py
-from transformers import CLIPVisionModelWithProjection
-
-image_encoder = CLIPVisionModelWithProjection.from_pretrained(
-    "laion/CLIP-ViT-H-14-laion2B-s32B-b79K",
-    torch_dtype=torch.float16,
-)
-
-pipeline = AutoPipelineForText2Image.from_pretrained(
-    "runwayml/stable-diffusion-v1-5",
-    image_encoder=image_encoder,
-    torch_dtype=torch.float16
-).to("cuda")
-
-pipeline.load_ip_adapter("h94/IP-Adapter-FaceID", subfolder=None, weight_name="ip-adapter-faceid-plus_sd15.bin")
-```

docs/source/en/using-diffusers/loading_overview.md

@@ -0,0 +1,17 @@
+<!--Copyright 2024 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License.
+-->
+
+# Overview
+
+🧨 Diffusers offers many pipelines, models, and schedulers for generative tasks. To make loading these components as simple as possible, we provide a single and unified method - `from_pretrained()` - that loads any of these components from either the Hugging Face [Hub](https://huggingface.co/models?library=diffusers&sort=downloads) or your local machine. Whenever you load a pipeline or model, the latest files are automatically downloaded and cached so you can quickly reuse them next time without redownloading the files.
+
+This section will show you everything you need to know about loading pipelines, how to load different components in a pipeline, how to load checkpoint variants, and how to load community pipelines. You'll also learn how to load schedulers and compare the speed and quality trade-offs of using different schedulers. Finally, you'll see how to convert and load KerasCV checkpoints so you can use them in PyTorch with 🧨 Diffusers.

docs/source/en/using-diffusers/merge_loras.md

@@ -1,266 +0,0 @@
-<!--Copyright 2024 The HuggingFace Team. All rights reserved.
-
-Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
-the License. You may obtain a copy of the License at
-
-http://www.apache.org/licenses/LICENSE-2.0
-
-Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
-an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
-specific language governing permissions and limitations under the License.
--->
-
-# Merge LoRAs
-
-It can be fun and creative to use multiple [LoRAs]((https://huggingface.co/docs/peft/conceptual_guides/adapter#low-rank-adaptation-lora)) together to generate something entirely new and unique. This works by merging multiple LoRA weights together to produce images that are a blend of different styles. Diffusers provides a few methods to merge LoRAs depending on *how* you want to merge their weights, which can affect image quality.
-
-This guide will show you how to merge LoRAs using the [`~loaders.UNet2DConditionLoadersMixin.set_adapters`] and [`~peft.LoraModel.add_weighted_adapter`] methods. To improve inference speed and reduce memory-usage of merged LoRAs, you'll also see how to use the [`~loaders.LoraLoaderMixin.fuse_lora`] method to fuse the LoRA weights with the original weights of the underlying model.
-
-For this guide, load a Stable Diffusion XL (SDXL) checkpoint and the [KappaNeuro/studio-ghibli-style]() and [Norod78/sdxl-chalkboarddrawing-lora]() LoRAs with the [`~loaders.LoraLoaderMixin.load_lora_weights`] method. You'll need to assign each LoRA an `adapter_name` to combine them later.
-
-```py
-from diffusers import DiffusionPipeline
-import torch
-
-pipeline = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=torch.float16).to("cuda")
-pipeline.load_lora_weights("ostris/ikea-instructions-lora-sdxl", weight_name="ikea_instructions_xl_v1_5.safetensors", adapter_name="ikea")
-pipeline.load_lora_weights("lordjia/by-feng-zikai", weight_name="fengzikai_v1.0_XL.safetensors", adapter_name="feng")
-```
-
-## set_adapters
-
-The [`~loaders.UNet2DConditionLoadersMixin.set_adapters`] method merges LoRA adapters by concatenating their weighted matrices. Use the adapter name to specify which LoRAs to merge, and the `adapter_weights` parameter to control the scaling for each LoRA. For example, if `adapter_weights=[0.5, 0.5]`, then the merged LoRA output is an average of both LoRAs. Try adjusting the adapter weights to see how it affects the generated image!
-
-```py
-pipeline.set_adapters(["ikea", "feng"], adapter_weights=[0.7, 0.8])
-
-generator = torch.manual_seed(0)
-prompt = "A bowl of ramen shaped like a cute kawaii bear, by Feng Zikai"
-image = pipeline(prompt, generator=generator, cross_attention_kwargs={"scale": 1.0}).images[0]
-image
-```
-
-<div class="flex justify-center">
-    <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/lora_merge_set_adapters.png"/>
-</div>
-
-## add_weighted_adapter
-
-> [!WARNING]
-> This is an experimental method that adds PEFTs [`~peft.LoraModel.add_weighted_adapter`] method to Diffusers to enable more efficient merging methods. Check out this [issue](https://github.com/huggingface/diffusers/issues/6892) if you're interested in learning more about the motivation and design behind this integration.
-
-The [`~peft.LoraModel.add_weighted_adapter`] method provides access to more efficient merging method such as [TIES and DARE](https://huggingface.co/docs/peft/developer_guides/model_merging). To use these merging methods, make sure you have the latest stable version of Diffusers and PEFT installed.
-
-```bash
-pip install -U diffusers peft
-```
-
-There are three steps to merge LoRAs with the [`~peft.LoraModel.add_weighted_adapter`] method:
-
-1. Create a [`~peft.PeftModel`] from the underlying model and LoRA checkpoint.
-2. Load a base UNet model and the LoRA adapters.
-3. Merge the adapters using the [`~peft.LoraModel.add_weighted_adapter`] method and the merging method of your choice.
-
-Let's dive deeper into what these steps entail.
-
-1. Load a UNet that corresponds to the UNet in the LoRA checkpoint. In this case, both LoRAs use the SDXL UNet as their base model.
-
-```python
-from diffusers import UNet2DConditionModel
-import torch
-
-unet = UNet2DConditionModel.from_pretrained(
-    "stabilityai/stable-diffusion-xl-base-1.0",
-    torch_dtype=torch.float16, 
-    use_safetensors=True,
-    variant="fp16",
-    subfolder="unet",
-).to("cuda")
-```
-
-Load the SDXL pipeline and the LoRA checkpoints, starting with the [ostris/ikea-instructions-lora-sdxl](https://huggingface.co/ostris/ikea-instructions-lora-sdxl) LoRA.
-
-```python
-from diffusers import DiffusionPipeline
-
-pipeline = DiffusionPipeline.from_pretrained(
-    "stabilityai/stable-diffusion-xl-base-1.0",
-    variant="fp16",
-    torch_dtype=torch.float16,
-    unet=unet
-).to("cuda")
-pipeline.load_lora_weights("ostris/ikea-instructions-lora-sdxl", weight_name="ikea_instructions_xl_v1_5.safetensors", adapter_name="ikea")
-```
-
-Now you'll create a [`~peft.PeftModel`] from the loaded LoRA checkpoint by combining the SDXL UNet and the LoRA UNet from the pipeline.
-
-```python
-from peft import get_peft_model, LoraConfig
-import copy
-
-sdxl_unet = copy.deepcopy(unet)
-ikea_peft_model = get_peft_model(
-    sdxl_unet,
-    pipeline.unet.peft_config["ikea"],
-    adapter_name="ikea"
-)
-
-original_state_dict = {f"base_model.model.{k}": v for k, v in pipeline.unet.state_dict().items()}
-ikea_peft_model.load_state_dict(original_state_dict, strict=True)
-```
-
-> [!TIP]
-> You can optionally push the ikea_peft_model to the Hub by calling `ikea_peft_model.push_to_hub("ikea_peft_model", token=TOKEN)`.
-
-Repeat this process to create a [`~peft.PeftModel`] from the [lordjia/by-feng-zikai](https://huggingface.co/lordjia/by-feng-zikai) LoRA.
-
-```python
-pipeline.delete_adapters("ikea")
-sdxl_unet.delete_adapters("ikea")
-
-pipeline.load_lora_weights("lordjia/by-feng-zikai", weight_name="fengzikai_v1.0_XL.safetensors", adapter_name="feng")
-pipeline.set_adapters(adapter_names="feng")
-
-feng_peft_model = get_peft_model(
-    sdxl_unet,
-    pipeline.unet.peft_config["feng"],
-    adapter_name="feng"
-)
-
-original_state_dict = {f"base_model.model.{k}": v for k, v in pipe.unet.state_dict().items()}
-feng_peft_model.load_state_dict(original_state_dict, strict=True)
-```
-
-2. Load a base UNet model and then load the adapters onto it.
-
-```python
-from peft import PeftModel
-
-base_unet = UNet2DConditionModel.from_pretrained(
-    "stabilityai/stable-diffusion-xl-base-1.0",
-    torch_dtype=torch.float16, 
-    use_safetensors=True,
-    variant="fp16",
-    subfolder="unet",
-).to("cuda")
-
-model = PeftModel.from_pretrained(base_unet, "stevhliu/ikea_peft_model", use_safetensors=True, subfolder="ikea", adapter_name="ikea")
-model.load_adapter("stevhliu/feng_peft_model", use_safetensors=True, subfolder="feng", adapter_name="feng")
-```
-
-3. Merge the adapters using the [`~peft.LoraModel.add_weighted_adapter`] method and the merging method of your choice (learn more about other merging methods in this [blog post](https://huggingface.co/blog/peft_merging)). For this example, let's use the `"dare_linear"` method to merge the LoRAs.
-
-> [!WARNING]
-> Keep in mind the LoRAs need to have the same rank to be merged!
-
-```python
-model.add_weighted_adapter(
-    adapters=["ikea", "feng"],
-    weights=[1.0, 1.0],
-    combination_type="dare_linear",
-    adapter_name="ikea-feng"
-)
-model.set_adapters("ikea-feng")
-```
-
-Now you can generate an image with the merged LoRA.
-
-```python
-model = model.to(dtype=torch.float16, device="cuda")
-
-pipeline = DiffusionPipeline.from_pretrained(
-    "stabilityai/stable-diffusion-xl-base-1.0", unet=model, variant="fp16", torch_dtype=torch.float16,
-).to("cuda")
-
-image = pipeline("A bowl of ramen shaped like a cute kawaii bear, by Feng Zikai", generator=torch.manual_seed(0)).images[0]
-image
-```
-
-<div class="flex justify-center">
-    <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/ikea-feng-dare-linear.png"/>
-</div>
-
-## fuse_lora
-
-Both the [`~loaders.UNet2DConditionLoadersMixin.set_adapters`] and [`~peft.LoraModel.add_weighted_adapter`] methods require loading the base model and the LoRA adapters separately which incurs some overhead. The [`~loaders.LoraLoaderMixin.fuse_lora`] method allows you to fuse the LoRA weights directly with the original weights of the underlying model. This way, you're only loading the model once which can increase inference and lower memory-usage.
-
-You can use PEFT to easily fuse/unfuse multiple adapters directly into the model weights (both UNet and text encoder) using the [`~loaders.LoraLoaderMixin.fuse_lora`] method, which can lead to a speed-up in inference and lower VRAM usage.
-
-For example, if you have a base model and adapters loaded and set as active with the following adapter weights:
-
-```py
-from diffusers import DiffusionPipeline
-import torch
-
-pipeline = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=torch.float16).to("cuda")
-pipeline.load_lora_weights("ostris/ikea-instructions-lora-sdxl", weight_name="ikea_instructions_xl_v1_5.safetensors", adapter_name="ikea")
-pipeline.load_lora_weights("lordjia/by-feng-zikai", weight_name="fengzikai_v1.0_XL.safetensors", adapter_name="feng")
-
-pipeline.set_adapters(["ikea", "feng"], adapter_weights=[0.7, 0.8])
-```
-
-Fuse these LoRAs into the UNet with the [`~loaders.LoraLoaderMixin.fuse_lora`] method. The `lora_scale` parameter controls how much to scale the output by with the LoRA weights. It is important to make the `lora_scale` adjustments in the [`~loaders.LoraLoaderMixin.fuse_lora`] method because it won’t work if you try to pass `scale` to the `cross_attention_kwargs` in the pipeline.
-
-```py
-pipeline.fuse_lora(adapter_names=["ikea", "feng"], lora_scale=1.0)
-```
-
-Then you should use [`~loaders.LoraLoaderMixin.unload_lora_weights`] to unload the LoRA weights since they've already been fused with the underlying base model. Finally, call [`~DiffusionPipeline.save_pretrained`] to save the fused pipeline locally or you could call [`~DiffusionPipeline.push_to_hub`] to push the fused pipeline to the Hub.
-
-```py
-pipeline.unload_lora_weights()
-# save locally
-pipeline.save_pretrained("path/to/fused-pipeline")
-# save to the Hub
-pipeline.push_to_hub("fused-ikea-feng")
-```
-
-Now you can quickly load the fused pipeline and use it for inference without needing to separately load the LoRA adapters.
-
-```py
-pipeline = DiffusionPipeline.from_pretrained(
-    "username/fused-ikea-feng", torch_dtype=torch.float16,
-).to("cuda")
-
-image = pipeline("A bowl of ramen shaped like a cute kawaii bear, by Feng Zikai", generator=torch.manual_seed(0)).images[0]
-image
-```
-
-You can call [`~loaders.LoraLoaderMixin.unfuse_lora`] to restore the original model's weights (for example, if you want to use a different `lora_scale` value). However, this only works if you've only fused one LoRA adapter to the original model. If you've fused multiple LoRAs, you'll need to reload the model.
-
-```py
-pipeline.unfuse_lora()
-```
-
-### torch.compile
-
-[torch.compile](../optimization/torch2.0#torchcompile) can speed up your pipeline even more, but the LoRA weights must be fused first and then unloaded. Typically, the UNet is compiled because it is such a computationally intensive component of the pipeline.
-
-```py
-from diffusers import DiffusionPipeline
-import torch
-
-# load base model and LoRAs
-pipeline = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=torch.float16).to("cuda")
-pipeline.load_lora_weights("ostris/ikea-instructions-lora-sdxl", weight_name="ikea_instructions_xl_v1_5.safetensors", adapter_name="ikea")
-pipeline.load_lora_weights("lordjia/by-feng-zikai", weight_name="fengzikai_v1.0_XL.safetensors", adapter_name="feng")
-
-# activate both LoRAs and set adapter weights
-pipeline.set_adapters(["ikea", "feng"], adapter_weights=[0.7, 0.8])
-
-# fuse LoRAs and unload weights
-pipeline.fuse_lora(adapter_names=["ikea", "feng"], lora_scale=1.0)
-pipeline.unload_lora_weights()
-
-# torch.compile
-pipeline.unet.to(memory_format=torch.channels_last)
-pipeline.unet = torch.compile(pipeline.unet, mode="reduce-overhead", fullgraph=True)
-
-image = pipeline("A bowl of ramen shaped like a cute kawaii bear, by Feng Zikai", generator=torch.manual_seed(0)).images[0]
-```
-
-Learn more about torch.compile in the [Accelerate inference of text-to-image diffusion models](../tutorials/fast_diffusion#torchcompile) guide.
-
-## Next steps
-
-For more conceptual details about how each merging method works, take a look at the [🤗 PEFT welcomes new merging methods](https://huggingface.co/blog/peft_merging#concatenation-cat) blog post!

docs/source/en/using-diffusers/schedulers.md

@@ -10,27 +10,57 @@ an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express o
 specific language governing permissions and limitations under the License.
 -->
 
-# Load schedulers and models
+# Schedulers
 
 [[open-in-colab]]
 
-Diffusion pipelines are a collection of interchangeable schedulers and models that can be mixed and matched to tailor a pipeline to a specific use case. The scheduler encapsulates the entire denoising process such as the number of denoising steps and the algorithm for finding the denoised sample. A scheduler is not parameterized or trained so they don't take very much memory. The model is usually only concerned with the forward pass of going from a noisy input to a less noisy sample.
+Diffusion pipelines are inherently a collection of diffusion models and schedulers that are partly independent from each other. This means that one is able to switch out parts of the pipeline to better customize
+a pipeline to one's use case. The best example of this is the [Schedulers](../api/schedulers/overview).
 
-This guide will show you how to load schedulers and models to customize a pipeline. You'll use the [runwayml/stable-diffusion-v1-5](https://hf.co/runwayml/stable-diffusion-v1-5) checkpoint throughout this guide, so let's load it first.
+Whereas diffusion models usually simply define the forward pass from noise to a less noisy sample,
+schedulers define the whole denoising process, *i.e.*:
+- How many denoising steps?
+- Stochastic or deterministic?
+- What algorithm to use to find the denoised sample?
 
-```py
-import torch
+They can be quite complex and often define a trade-off between **denoising speed** and **denoising quality**.
+It is extremely difficult to measure quantitatively which scheduler works best for a given diffusion pipeline, so it is often recommended to simply try out which works best.
+
+The following paragraphs show how to do so with the 🧨 Diffusers library.
+
+## Load pipeline
+
+Let's start by loading the [`runwayml/stable-diffusion-v1-5`](https://huggingface.co/runwayml/stable-diffusion-v1-5) model in the [`DiffusionPipeline`]:
+
+```python
+from huggingface_hub import login
 from diffusers import DiffusionPipeline
+import torch
+
+login()
 
 pipeline = DiffusionPipeline.from_pretrained(
     "runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16, use_safetensors=True
-).to("cuda")
+)
 ```
 
-You can see what scheduler this pipeline uses with the `pipeline.scheduler` attribute.
+Next, we move it to GPU:
 
-```py
+```python
+pipeline.to("cuda")
+```
+
+## Access the scheduler
+
+The scheduler is always one of the components of the pipeline and is usually called `"scheduler"`.
+So it can be accessed via the `"scheduler"` property.
+
+```python
 pipeline.scheduler
+```
+
+**Output**:
+```
 PNDMScheduler {
   "_class_name": "PNDMScheduler",
   "_diffusers_version": "0.21.4",
@@ -47,156 +77,235 @@ PNDMScheduler {
 }
 ```
 
-## Load a scheduler
-
-Schedulers are defined by a configuration file that can be used by a variety of schedulers. Load a scheduler with the [`SchedulerMixin.from_pretrained`] method, and specify the `subfolder` parameter to load the configuration file into the correct subfolder of the pipeline repository.
-
-For example, to load the [`DDIMScheduler`]:
-
-```py
-from diffusers import DDIMScheduler, DiffusionPipeline
-
-ddim = DDIMScheduler.from_pretrained("runwayml/stable-diffusion-v1-5", subfolder="scheduler")
-```
-
-Then you can pass the newly loaded scheduler to the pipeline.
+We can see that the scheduler is of type [`PNDMScheduler`].
+Cool, now let's compare the scheduler in its performance to other schedulers.
+First we define a prompt on which we will test all the different schedulers:
 
 ```python
-pipeline = DiffusionPipeline.from_pretrained(
-    "runwayml/stable-diffusion-v1-5", scheduler=ddim, torch_dtype=torch.float16, use_safetensors=True
-).to("cuda")
+prompt = "A photograph of an astronaut riding a horse on Mars, high resolution, high definition."
 ```
 
+Next, we create a generator from a random seed that will ensure that we can generate similar images as well as run the pipeline:
+
+```python
+generator = torch.Generator(device="cuda").manual_seed(8)
+image = pipeline(prompt, generator=generator).images[0]
+image
+```
+
+<p align="center">
+    <br>
+    <img src="https://huggingface.co/datasets/patrickvonplaten/images/resolve/main/diffusers_docs/astronaut_pndm.png" width="400"/>
+    <br>
+</p>
+
+
+## Changing the scheduler
+
+Now we show how easy it is to change the scheduler of a pipeline. Every scheduler has a property [`~SchedulerMixin.compatibles`]
+which defines all compatible schedulers. You can take a look at all available, compatible schedulers for the Stable Diffusion pipeline as follows.
+
+```python
+pipeline.scheduler.compatibles
+```
+
+**Output**:
+```
+[diffusers.utils.dummy_torch_and_torchsde_objects.DPMSolverSDEScheduler,
+ diffusers.schedulers.scheduling_euler_discrete.EulerDiscreteScheduler,
+ diffusers.schedulers.scheduling_lms_discrete.LMSDiscreteScheduler,
+ diffusers.schedulers.scheduling_ddim.DDIMScheduler,
+ diffusers.schedulers.scheduling_ddpm.DDPMScheduler,
+ diffusers.schedulers.scheduling_heun_discrete.HeunDiscreteScheduler,
+ diffusers.schedulers.scheduling_dpmsolver_multistep.DPMSolverMultistepScheduler,
+ diffusers.schedulers.scheduling_deis_multistep.DEISMultistepScheduler,
+ diffusers.schedulers.scheduling_pndm.PNDMScheduler,
+ diffusers.schedulers.scheduling_euler_ancestral_discrete.EulerAncestralDiscreteScheduler,
+ diffusers.schedulers.scheduling_unipc_multistep.UniPCMultistepScheduler,
+ diffusers.schedulers.scheduling_k_dpm_2_discrete.KDPM2DiscreteScheduler,
+ diffusers.schedulers.scheduling_dpmsolver_singlestep.DPMSolverSinglestepScheduler,
+ diffusers.schedulers.scheduling_k_dpm_2_ancestral_discrete.KDPM2AncestralDiscreteScheduler]
+```
+
+Cool, lots of schedulers to look at. Feel free to have a look at their respective class definitions:
+
+- [`EulerDiscreteScheduler`],
+- [`LMSDiscreteScheduler`],
+- [`DDIMScheduler`],
+- [`DDPMScheduler`],
+- [`HeunDiscreteScheduler`],
+- [`DPMSolverMultistepScheduler`],
+- [`DEISMultistepScheduler`],
+- [`PNDMScheduler`],
+- [`EulerAncestralDiscreteScheduler`],
+- [`UniPCMultistepScheduler`],
+- [`KDPM2DiscreteScheduler`],
+- [`DPMSolverSinglestepScheduler`],
+- [`KDPM2AncestralDiscreteScheduler`].
+
+We will now compare the input prompt with all other schedulers. To change the scheduler of the pipeline you can make use of the
+convenient [`~ConfigMixin.config`] property in combination with the [`~ConfigMixin.from_config`] function.
+
+```python
+pipeline.scheduler.config
+```
+
+returns a dictionary of the configuration of the scheduler:
+
+**Output**:
+```py
+FrozenDict([('num_train_timesteps', 1000),
+            ('beta_start', 0.00085),
+            ('beta_end', 0.012),
+            ('beta_schedule', 'scaled_linear'),
+            ('trained_betas', None),
+            ('skip_prk_steps', True),
+            ('set_alpha_to_one', False),
+            ('prediction_type', 'epsilon'),
+            ('timestep_spacing', 'leading'),
+            ('steps_offset', 1),
+            ('_use_default_values', ['timestep_spacing', 'prediction_type']),
+            ('_class_name', 'PNDMScheduler'),
+            ('_diffusers_version', '0.21.4'),
+            ('clip_sample', False)])
+```
+
+This configuration can then be used to instantiate a scheduler
+of a different class that is compatible with the pipeline. Here,
+we change the scheduler to the [`DDIMScheduler`].
+
+```python
+from diffusers import DDIMScheduler
+
+pipeline.scheduler = DDIMScheduler.from_config(pipeline.scheduler.config)
+```
+
+Cool, now we can run the pipeline again to compare the generation quality.
+
+```python
+generator = torch.Generator(device="cuda").manual_seed(8)
+image = pipeline(prompt, generator=generator).images[0]
+image
+```
+
+<p align="center">
+    <br>
+    <img src="https://huggingface.co/datasets/patrickvonplaten/images/resolve/main/diffusers_docs/astronaut_ddim.png" width="400"/>
+    <br>
+</p>
+
+If you are a JAX/Flax user, please check [this section](#changing-the-scheduler-in-flax) instead.
+
 ## Compare schedulers
 
-Schedulers have their own unique strengths and weaknesses, making it difficult to quantitatively compare which scheduler works best for a pipeline. You typically have to make a trade-off between denoising speed and denoising quality. We recommend trying out different schedulers to find one that works best for your use case. Call the `pipeline.scheduler.compatibles` attribute to see what schedulers are compatible with a pipeline.
+So far we have tried running the stable diffusion pipeline with two schedulers: [`PNDMScheduler`] and [`DDIMScheduler`].
+A number of better schedulers have been released that can be run with much fewer steps; let's compare them here:
 
-Let's compare the [`LMSDiscreteScheduler`], [`EulerDiscreteScheduler`], [`EulerAncestralDiscreteScheduler`], and the [`DPMSolverMultistepScheduler`] on the following prompt and seed.
+[`LMSDiscreteScheduler`] usually leads to better results:
 
-```py
-import torch
-from diffusers import DiffusionPipeline
-
-pipeline = DiffusionPipeline.from_pretrained(
-    "runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16, use_safetensors=True
-).to("cuda")
-
-prompt = "A photograph of an astronaut riding a horse on Mars, high resolution, high definition."
-generator = torch.Generator(device="cuda").manual_seed(8)
-```
-
-To change the pipelines scheduler, use the [`~ConfigMixin.from_config`] method to load a different scheduler's `pipeline.scheduler.config` into the pipeline.
-
-<hfoptions id="schedulers">
-<hfoption id="LMSDiscreteScheduler">
-
-[`LMSDiscreteScheduler`] typically generates higher quality images than the default scheduler.
-
-```py
+```python
 from diffusers import LMSDiscreteScheduler
 
 pipeline.scheduler = LMSDiscreteScheduler.from_config(pipeline.scheduler.config)
+
+generator = torch.Generator(device="cuda").manual_seed(8)
 image = pipeline(prompt, generator=generator).images[0]
 image
 ```
 
-</hfoption>
-<hfoption id="EulerDiscreteScheduler">
+<p align="center">
+    <br>
+    <img src="https://huggingface.co/datasets/patrickvonplaten/images/resolve/main/diffusers_docs/astronaut_lms.png" width="400"/>
+    <br>
+</p>
 
-[`EulerDiscreteScheduler`] can generate higher quality images in just 30 steps.
 
-```py
+[`EulerDiscreteScheduler`] and [`EulerAncestralDiscreteScheduler`] can generate high quality results with as little as 30 steps.
+
+```python
 from diffusers import EulerDiscreteScheduler
 
 pipeline.scheduler = EulerDiscreteScheduler.from_config(pipeline.scheduler.config)
-image = pipeline(prompt, generator=generator).images[0]
+
+generator = torch.Generator(device="cuda").manual_seed(8)
+image = pipeline(prompt, generator=generator, num_inference_steps=30).images[0]
 image
 ```
 
-</hfoption>
-<hfoption id="EulerAncestralDiscreteScheduler">
+<p align="center">
+    <br>
+    <img src="https://huggingface.co/datasets/patrickvonplaten/images/resolve/main/diffusers_docs/astronaut_euler_discrete.png" width="400"/>
+    <br>
+</p>
 
-[`EulerAncestralDiscreteScheduler`] can generate higher quality images in just 30 steps.
 
-```py
+and:
+
+```python
 from diffusers import EulerAncestralDiscreteScheduler
 
 pipeline.scheduler = EulerAncestralDiscreteScheduler.from_config(pipeline.scheduler.config)
-image = pipeline(prompt, generator=generator).images[0]
+
+generator = torch.Generator(device="cuda").manual_seed(8)
+image = pipeline(prompt, generator=generator, num_inference_steps=30).images[0]
 image
 ```
 
-</hfoption>
-<hfoption id="DPMSolverMultistepScheduler">
+<p align="center">
+    <br>
+    <img src="https://huggingface.co/datasets/patrickvonplaten/images/resolve/main/diffusers_docs/astronaut_euler_ancestral.png" width="400"/>
+    <br>
+</p>
 
-[`DPMSolverMultistepScheduler`] provides a balance between speed and quality and can generate higher quality images in just 20 steps.
 
-```py
+[`DPMSolverMultistepScheduler`] gives a reasonable speed/quality trade-off and can be run with as little as 20 steps.
+
+```python
 from diffusers import DPMSolverMultistepScheduler
 
 pipeline.scheduler = DPMSolverMultistepScheduler.from_config(pipeline.scheduler.config)
-image = pipeline(prompt, generator=generator).images[0]
+
+generator = torch.Generator(device="cuda").manual_seed(8)
+image = pipeline(prompt, generator=generator, num_inference_steps=20).images[0]
 image
 ```
 
-</hfoption>
-</hfoptions>
+<p align="center">
+    <br>
+    <img src="https://huggingface.co/datasets/patrickvonplaten/images/resolve/main/diffusers_docs/astronaut_dpm.png" width="400"/>
+    <br>
+</p>
 
-<div class="flex gap-4">
-  <div>
-    <img class="rounded-xl" src="https://huggingface.co/datasets/patrickvonplaten/images/resolve/main/diffusers_docs/astronaut_lms.png" />
-    <figcaption class="mt-2 text-center text-sm text-gray-500">LMSDiscreteScheduler</figcaption>
-  </div>
-  <div>
-    <img class="rounded-xl" src="https://huggingface.co/datasets/patrickvonplaten/images/resolve/main/diffusers_docs/astronaut_euler_discrete.png" />
-    <figcaption class="mt-2 text-center text-sm text-gray-500">EulerDiscreteScheduler</figcaption>
-  </div>
-</div>
-<div class="flex gap-4">
-  <div>
-    <img class="rounded-xl" src="https://huggingface.co/datasets/patrickvonplaten/images/resolve/main/diffusers_docs/astronaut_euler_ancestral.png" />
-    <figcaption class="mt-2 text-center text-sm text-gray-500">EulerAncestralDiscreteScheduler</figcaption>
-  </div>
-  <div>
-    <img class="rounded-xl" src="https://huggingface.co/datasets/patrickvonplaten/images/resolve/main/diffusers_docs/astronaut_dpm.png" />
-    <figcaption class="mt-2 text-center text-sm text-gray-500">DPMSolverMultistepScheduler</figcaption>
-  </div>
-</div>
+As you can see, most images look very similar and are arguably of very similar quality. It often really depends on the specific use case which scheduler to choose. A good approach is always to run multiple different
+schedulers to compare results.
 
-Most images look very similar and are comparable in quality. Again, it often comes down to your specific use case so a good approach is to run multiple different schedulers and compare the results.
+## Changing the Scheduler in Flax
 
-### Flax schedulers
+If you are a JAX/Flax user, you can also change the default pipeline scheduler. This is a complete example of how to run inference using the Flax Stable Diffusion pipeline and the super-fast [DPM-Solver++ scheduler](../api/schedulers/multistep_dpm_solver):
 
-To compare Flax schedulers, you need to additionally load the scheduler state into the model parameters. For example, let's change the default scheduler in [`FlaxStableDiffusionPipeline`] to use the super fast [`FlaxDPMSolverMultistepScheduler`].
-
-> [!WARNING]
-> The [`FlaxLMSDiscreteScheduler`] and [`FlaxDDPMScheduler`] are not compatible with the [`FlaxStableDiffusionPipeline`] yet.
-
-```py
+```Python
 import jax
 import numpy as np
 from flax.jax_utils import replicate
 from flax.training.common_utils import shard
+
 from diffusers import FlaxStableDiffusionPipeline, FlaxDPMSolverMultistepScheduler
 
+model_id = "runwayml/stable-diffusion-v1-5"
 scheduler, scheduler_state = FlaxDPMSolverMultistepScheduler.from_pretrained(
-    "runwayml/stable-diffusion-v1-5",
+    model_id,
     subfolder="scheduler"
 )
 pipeline, params = FlaxStableDiffusionPipeline.from_pretrained(
-    "runwayml/stable-diffusion-v1-5",
+    model_id,
     scheduler=scheduler,
     revision="bf16",
     dtype=jax.numpy.bfloat16,
 )
 params["scheduler"] = scheduler_state
-```
 
-Then you can take advantage of Flax's compatibility with TPUs to generate a number of images in parallel. You'll need to make a copy of the model parameters for each available device and then split the inputs across them to generate your desired number of images.
-
-```py
 # Generate 1 image per parallel device (8 on TPUv2-8 or TPUv3-8)
-prompt = "A photograph of an astronaut riding a horse on Mars, high resolution, high definition."
+prompt = "a photo of an astronaut riding a horse on mars"
 num_samples = jax.device_count()
 prompt_ids = pipeline.prepare_inputs([prompt] * num_samples)
 
@@ -212,33 +321,11 @@ images = pipeline(prompt_ids, params, prng_seed, num_inference_steps, jit=True).
 images = pipeline.numpy_to_pil(np.asarray(images.reshape((num_samples,) + images.shape[-3:])))
 ```
 
-## Models
+<Tip warning={true}>
 
-Models are loaded from the [`ModelMixin.from_pretrained`] method, which downloads and caches the latest version of the model weights and configurations. If the latest files are available in the local cache, [`~ModelMixin.from_pretrained`] reuses files in the cache instead of re-downloading them.
+The following Flax schedulers are _not yet compatible_ with the Flax Stable Diffusion Pipeline:
 
-Models can be loaded from a subfolder with the `subfolder` argument. For example, the model weights for [runwayml/stable-diffusion-v1-5](https://hf.co/runwayml/stable-diffusion-v1-5) are stored in the [unet](https://hf.co/runwayml/stable-diffusion-v1-5/tree/main/unet) subfolder.
+- `FlaxLMSDiscreteScheduler`
+- `FlaxDDPMScheduler`
 
-```python
-from diffusers import UNet2DConditionModel
-
-unet = UNet2DConditionModel.from_pretrained("runwayml/stable-diffusion-v1-5", subfolder="unet", use_safetensors=True)
-```
-
-They can also be directly loaded from a [repository](https://huggingface.co/google/ddpm-cifar10-32/tree/main).
-
-```python
-from diffusers import UNet2DModel
-
-unet = UNet2DModel.from_pretrained("google/ddpm-cifar10-32", use_safetensors=True)
-```
-
-To load and save model variants, specify the `variant` argument in [`ModelMixin.from_pretrained`] and [`ModelMixin.save_pretrained`].
-
-```python
-from diffusers import UNet2DConditionModel
-
-unet = UNet2DConditionModel.from_pretrained(
-    "runwayml/stable-diffusion-v1-5", subfolder="unet", variant="non_ema", use_safetensors=True
-)
-unet.save_pretrained("./local-unet", variant="non_ema")
-```
+</Tip>

docs/source/en/using-diffusers/sdxl.md

@@ -63,12 +63,11 @@ from diffusers import StableDiffusionXLPipeline, StableDiffusionXLImg2ImgPipelin
 import torch
 
 pipeline = StableDiffusionXLPipeline.from_single_file(
-    "https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/blob/main/sd_xl_base_1.0.safetensors", 
-    torch_dtype=torch.float16
+    "https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/blob/main/sd_xl_base_1.0.safetensors", torch_dtype=torch.float16, variant="fp16", use_safetensors=True
 ).to("cuda")
 
 refiner = StableDiffusionXLImg2ImgPipeline.from_single_file(
-    "https://huggingface.co/stabilityai/stable-diffusion-xl-refiner-1.0/blob/main/sd_xl_refiner_1.0.safetensors", torch_dtype=torch.float16
+    "https://huggingface.co/stabilityai/stable-diffusion-xl-refiner-1.0/blob/main/sd_xl_refiner_1.0.safetensors", torch_dtype=torch.float16, use_safetensors=True, variant="fp16"
 ).to("cuda")
 ```
 

docs/source/en/using-diffusers/sdxl_turbo.md

@@ -31,31 +31,29 @@ Before you begin, make sure you have the following libraries installed:
 Model weights may be stored in separate subfolders on the Hub or locally, in which case, you should use the [`~StableDiffusionXLPipeline.from_pretrained`] method:
 
 ```py
-from diffusers import AutoPipelineForText2Image
+from diffusers import AutoPipelineForText2Image, AutoPipelineForImage2Image
 import torch
 
 pipeline = AutoPipelineForText2Image.from_pretrained("stabilityai/sdxl-turbo", torch_dtype=torch.float16, variant="fp16")
 pipeline = pipeline.to("cuda")
 ```
 
-You can also use the [`~StableDiffusionXLPipeline.from_single_file`] method to load a model checkpoint stored in a single file format (`.ckpt` or `.safetensors`) from the Hub or locally. For this loading method, you need to set `timestep_spacing="trailing"` (feel free to experiment with the other scheduler config values to get better results):
+You can also use the [`~StableDiffusionXLPipeline.from_single_file`] method to load a model checkpoint stored in a single file format (`.ckpt` or `.safetensors`) from the Hub or locally:
 
 ```py
-from diffusers import StableDiffusionXLPipeline, EulerAncestralDiscreteScheduler
+from diffusers import StableDiffusionXLPipeline
 import torch
 
 pipeline = StableDiffusionXLPipeline.from_single_file(
-    "https://huggingface.co/stabilityai/sdxl-turbo/blob/main/sd_xl_turbo_1.0_fp16.safetensors",
-    torch_dtype=torch.float16, variant="fp16")
+    "https://huggingface.co/stabilityai/sdxl-turbo/blob/main/sd_xl_turbo_1.0_fp16.safetensors", torch_dtype=torch.float16)
 pipeline = pipeline.to("cuda")
-pipeline.scheduler = EulerAncestralDiscreteScheduler.from_config(pipeline.scheduler.config, timestep_spacing="trailing")
 ```
 
 ## Text-to-image
 
 For text-to-image, pass a text prompt. By default, SDXL Turbo generates a 512x512 image, and that resolution gives the best results. You can try setting the `height` and `width` parameters to 768x768 or 1024x1024, but you should expect quality degradations when doing so.
 
-Make sure to set `guidance_scale` to 0.0 to disable, as the model was trained without it. A single inference step is enough to generate high quality images.
+Make sure to set `guidance_scale` to 0.0 to disable, as the model was trained without it. A single inference step is enough to generate high quality images. 
 Increasing the number of steps to 2, 3 or 4 should improve image quality.
 
 ```py
@@ -77,7 +75,7 @@ image
 
 ## Image-to-image
 
-For image-to-image generation, make sure that `num_inference_steps * strength` is larger or equal to 1.
+For image-to-image generation, make sure that `num_inference_steps * strength` is larger or equal to 1. 
 The image-to-image pipeline will run for `int(num_inference_steps * strength)` steps, e.g. `0.5 * 2.0 = 1` step in
 our example below.
 
@@ -86,14 +84,14 @@ from diffusers import AutoPipelineForImage2Image
 from diffusers.utils import load_image, make_image_grid
 
 # use from_pipe to avoid consuming additional memory when loading a checkpoint
-pipeline_image2image = AutoPipelineForImage2Image.from_pipe(pipeline_text2image).to("cuda")
+pipeline = AutoPipelineForImage2Image.from_pipe(pipeline_text2image).to("cuda")
 
 init_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png")
 init_image = init_image.resize((512, 512))
 
 prompt = "cat wizard, gandalf, lord of the rings, detailed, fantasy, cute, adorable, Pixar, Disney, 8k"
 
-image = pipeline_image2image(prompt, image=init_image, strength=0.5, guidance_scale=0.0, num_inference_steps=2).images[0]
+image = pipeline(prompt, image=init_image, strength=0.5, guidance_scale=0.0, num_inference_steps=2).images[0]
 make_image_grid([init_image, image], rows=1, cols=2)
 ```
 
@@ -103,7 +101,7 @@ make_image_grid([init_image, image], rows=1, cols=2)
 
 ## Speed-up SDXL Turbo even more
 
-- Compile the UNet if you are using PyTorch version 2.0 or higher. The first inference run will be very slow, but subsequent ones will be much faster.
+- Compile the UNet if you are using PyTorch version 2 or better. The first inference run will be very slow, but subsequent ones will be much faster.
 
 ```py
 pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)

docs/source/en/using-diffusers/stable_diffusion_jax_how_to.md

@@ -217,9 +217,3 @@ Check your image dimensions to see if they're correct:
 images.shape
 # (8, 1, 512, 512, 3)
 ```
-
-## Resources
-
-To learn more about how JAX works with Stable Diffusion, you may be interested in reading:
-
-* [Accelerating Stable Diffusion XL Inference with JAX on Cloud TPU v5e](https://hf.co/blog/sdxl_jax)

docs/source/en/using-diffusers/svd.md

@@ -21,7 +21,7 @@ This guide will show you how to use SVD to generate short videos from images.
 Before you begin, make sure you have the following libraries installed:
 
 ```py
-!pip install -q -U diffusers transformers accelerate
+!pip install -q -U diffusers transformers accelerate 
 ```
 
 The are two variants of this model, [SVD](https://huggingface.co/stabilityai/stable-video-diffusion-img2vid) and [SVD-XT](https://huggingface.co/stabilityai/stable-video-diffusion-img2vid-xt). The SVD checkpoint is trained to generate 14 frames and the SVD-XT checkpoint is further finetuned to generate 25 frames.
@@ -86,7 +86,7 @@ Video generation is very memory intensive because you're essentially generating
 + frames = pipe(image, decode_chunk_size=2, generator=generator, num_frames=25).frames[0]
 ```
 
-Using all these tricks together should lower the memory requirement to less than 8GB VRAM.
+Using all these tricks togethere should lower the memory requirement to less than 8GB VRAM.
 
 ## Micro-conditioning
 

docs/source/en/using-diffusers/t2i_adapter.md

@@ -1,219 +0,0 @@
-<!--Copyright 2024 The HuggingFace Team. All rights reserved.
-
-Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
-the License. You may obtain a copy of the License at
-
-http://www.apache.org/licenses/LICENSE-2.0
-
-Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
-an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
-specific language governing permissions and limitations under the License.
--->
-
-# T2I-Adapter
-
-[T2I-Adapter](https://hf.co/papers/2302.08453) is a lightweight adapter for controlling and providing more accurate
-structure guidance for text-to-image models. It works by learning an alignment between the internal knowledge of the
-text-to-image model and an external control signal, such as edge detection or depth estimation.
-
-The T2I-Adapter design is simple, the condition is passed to four feature extraction blocks and three downsample
-blocks. This makes it fast and easy to train different adapters for different conditions which can be plugged into the
-text-to-image model. T2I-Adapter is similar to [ControlNet](controlnet) except it is smaller (~77M parameters) and
-faster because it only runs once during the diffusion process. The downside is that performance may be slightly worse
-than ControlNet.
-
-This guide will show you how to use T2I-Adapter with different Stable Diffusion models and how you can compose multiple
-T2I-Adapters to impose more than one condition.
-
-> [!TIP]
-> There are several T2I-Adapters available for different conditions, such as color palette, depth, sketch, pose, and
-> segmentation. Check out the [TencentARC](https://hf.co/TencentARC) repository to try them out!
-
-Before you begin, make sure you have the following libraries installed.
-
-```py
-# uncomment to install the necessary libraries in Colab
-#!pip install -q diffusers accelerate controlnet-aux==0.0.7
-```
-
-## Text-to-image
-
-Text-to-image models rely on a prompt to generate an image, but sometimes, text alone may not be enough to provide more
-accurate structural guidance. T2I-Adapter allows you to provide an additional control image to guide the generation
-process. For example, you can provide a canny image (a white outline of an image on a black background) to guide the
-model to generate an image with a similar structure.
-
-<hfoptions id="stablediffusion">
-<hfoption id="Stable Diffusion 1.5">
-
-Create a canny image with the [opencv-library](https://github.com/opencv/opencv-python).
-
-```py
-import cv2
-import numpy as np
-from PIL import Image
-from diffusers.utils import load_image
-
-image = load_image("https://huggingface.co/datasets/hf-internal-testing/diffusers-images/resolve/main/sd_controlnet/hf-logo.png")
-image = np.array(image)
-
-low_threshold = 100
-high_threshold = 200
-
-image = cv2.Canny(image, low_threshold, high_threshold)
-image = Image.fromarray(image)
-```
-
-Now load a T2I-Adapter conditioned on [canny images](https://hf.co/TencentARC/t2iadapter_canny_sd15v2) and pass it to
-the [`StableDiffusionAdapterPipeline`].
-
-```py
-import torch
-from diffusers import StableDiffusionAdapterPipeline, T2IAdapter
-
-adapter = T2IAdapter.from_pretrained("TencentARC/t2iadapter_canny_sd15v2", torch_dtype=torch.float16)
-pipeline = StableDiffusionAdapterPipeline.from_pretrained(
-    "runwayml/stable-diffusion-v1-5",
-    adapter=adapter,
-    torch_dtype=torch.float16,
-)
-pipeline.to("cuda")
-```
-
-Finally, pass your prompt and control image to the pipeline.
-
-```py
-generator = torch.Generator("cuda").manual_seed(0)
-
-image = pipeline(
-    prompt="cinematic photo of a plush and soft midcentury style rug on a wooden floor, 35mm photograph, film, professional, 4k, highly detailed",
-    image=image,
-    generator=generator,
-).images[0]
-image
-```
-
-<div class="flex justify-center">
-  <img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/t2i-sd1.5.png"/>
-</div>
-
-</hfoption>
-<hfoption id="Stable Diffusion XL">
-
-Create a canny image with the [controlnet-aux](https://github.com/huggingface/controlnet_aux) library.
-
-```py
-from controlnet_aux.canny import CannyDetector
-from diffusers.utils import load_image
-
-canny_detector = CannyDetector()
-
-image = load_image("https://huggingface.co/datasets/hf-internal-testing/diffusers-images/resolve/main/sd_controlnet/hf-logo.png")
-image = canny_detector(image, detect_resolution=384, image_resolution=1024)
-```
-
-Now load a T2I-Adapter conditioned on [canny images](https://hf.co/TencentARC/t2i-adapter-canny-sdxl-1.0) and pass it
-to the [`StableDiffusionXLAdapterPipeline`].
-
-```py
-import torch
-from diffusers import StableDiffusionXLAdapterPipeline, T2IAdapter, EulerAncestralDiscreteScheduler, AutoencoderKL
-
-scheduler = EulerAncestralDiscreteScheduler.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", subfolder="scheduler")
-vae = AutoencoderKL.from_pretrained("madebyollin/sdxl-vae-fp16-fix", torch_dtype=torch.float16)
-adapter = T2IAdapter.from_pretrained("TencentARC/t2i-adapter-canny-sdxl-1.0", torch_dtype=torch.float16)
-pipeline = StableDiffusionXLAdapterPipeline.from_pretrained(
-    "stabilityai/stable-diffusion-xl-base-1.0",
-    adapter=adapter,
-    vae=vae,
-    scheduler=scheduler,
-    torch_dtype=torch.float16,
-    variant="fp16",
-)
-pipeline.to("cuda")
-```
-
-Finally, pass your prompt and control image to the pipeline.
-
-```py
-generator = torch.Generator("cuda").manual_seed(0)
-
-image = pipeline(
-  prompt="cinematic photo of a plush and soft midcentury style rug on a wooden floor, 35mm photograph, film, professional, 4k, highly detailed",
-  image=image,
-  generator=generator,
-).images[0]
-image
-```
-
-<div class="flex justify-center">
-  <img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/t2i-sdxl.png"/>
-</div>
-
-</hfoption>
-</hfoptions>
-
-## MultiAdapter
-
-T2I-Adapters are also composable, allowing you to use more than one adapter to impose multiple control conditions on an
-image. For example, you can use a pose map to provide structural control and a depth map for depth control. This is
-enabled by the [`MultiAdapter`] class.
-
-Let's condition a text-to-image model with a pose and depth adapter. Create and place your depth and pose image and in a list.
-
-```py
-from diffusers.utils import load_image
-
-pose_image = load_image(
-    "https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/keypose_sample_input.png"
-)
-depth_image = load_image(
-    "https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/depth_sample_input.png"
-)
-cond = [pose_image, depth_image]
-prompt = ["Santa Claus walking into an office room with a beautiful city view"]
-```
-
-<div class="flex gap-4">
-  <div>
-    <img class="rounded-xl" src="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/depth_sample_input.png"/>
-    <figcaption class="mt-2 text-center text-sm text-gray-500">depth image</figcaption>
-  </div>
-  <div>
-    <img class="rounded-xl" src="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/keypose_sample_input.png"/>
-    <figcaption class="mt-2 text-center text-sm text-gray-500">pose image</figcaption>
-  </div>
-</div>
-
-Load the corresponding pose and depth adapters as a list in the [`MultiAdapter`] class.
-
-```py
-import torch
-from diffusers import StableDiffusionAdapterPipeline, MultiAdapter, T2IAdapter
-
-adapters = MultiAdapter(
-    [
-        T2IAdapter.from_pretrained("TencentARC/t2iadapter_keypose_sd14v1"),
-        T2IAdapter.from_pretrained("TencentARC/t2iadapter_depth_sd14v1"),
-    ]
-)
-adapters = adapters.to(torch.float16)
-```
-
-Finally, load a [`StableDiffusionAdapterPipeline`] with the adapters, and pass your prompt and conditioned images to
-it. Use the [`adapter_conditioning_scale`] to adjust the weight of each adapter on the image.
-
-```py
-pipeline = StableDiffusionAdapterPipeline.from_pretrained(
-    "CompVis/stable-diffusion-v1-4",
-    torch_dtype=torch.float16,
-    adapter=adapters,
-).to("cuda")
-
-image = pipeline(prompt, cond, adapter_conditioning_scale=[0.7, 0.7]).images[0]
-image
-```
-
-<div class="flex justify-center">
-  <img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/t2i-multi.png"/>
-</div>

docs/source/en/using-diffusers/weighted_prompts.md

@@ -10,209 +10,10 @@ an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express o
 specific language governing permissions and limitations under the License.
 -->
 
-# Prompt techniques
+# Prompt weighting
 
 [[open-in-colab]]
 
-Prompts are important because they describe what you want a diffusion model to generate. The best prompts are detailed, specific, and well-structured to help the model realize your vision. But crafting a great prompt takes time and effort and sometimes it may not be enough because language and words can be imprecise. This is where you need to boost your prompt with other techniques, such as prompt enhancing and prompt weighting, to get the results you want.
-
-This guide will show you how you can use these prompt techniques to generate high-quality images with lower effort and adjust the weight of certain keywords in a prompt.
-
-## Prompt engineering
-
-> [!TIP]
-> This is not an exhaustive guide on prompt engineering, but it will help you understand the necessary parts of a good prompt. We encourage you to continue experimenting with different prompts and combine them in new ways to see what works best. As you write more prompts, you'll develop an intuition for what works and what doesn't!
-
-New diffusion models do a pretty good job of generating high-quality images from a basic prompt, but it is still important to create a well-written prompt to get the best results. Here are a few tips for writing a good prompt:
-
-1. What is the image *medium*? Is it a photo, a painting, a 3D illustration, or something else?
-2. What is the image *subject*? Is it a person, animal, object, or scene?
-3. What *details* would you like to see in the image? This is where you can get really creative and have a lot of fun experimenting with different words to bring your image to life. For example, what is the lighting like? What is the vibe and aesthetic? What kind of art or illustration style are you looking for? The more specific and precise words you use, the better the model will understand what you want to generate.
-
-<div class="flex gap-4">
-  <div>
-    <img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/plain-prompt.png"/>
-    <figcaption class="mt-2 text-center text-sm text-gray-500">"A photo of a banana-shaped couch in a living room"</figcaption>
-  </div>
-  <div>
-    <img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/detail-prompt.png"/>
-    <figcaption class="mt-2 text-center text-sm text-gray-500">"A vibrant yellow banana-shaped couch sits in a cozy living room, its curve cradling a pile of colorful cushions. on the wooden floor, a patterned rug adds a touch of eclectic charm, and a potted plant sits in the corner, reaching towards the sunlight filtering through the windows"</figcaption>
-  </div>
-</div>
-
-## Prompt enhancing with GPT2
-
-Prompt enhancing is a technique for quickly improving prompt quality without spending too much effort constructing one. It uses a model like GPT2 pretrained on Stable Diffusion text prompts to automatically enrich a prompt with additional important keywords to generate high-quality images.
-
-The technique works by curating a list of specific keywords and forcing the model to generate those words to enhance the original prompt. This way, your prompt can be "a cat" and GPT2 can enhance the prompt to "cinematic film still of a cat basking in the sun on a roof in Turkey, highly detailed, high budget hollywood movie, cinemascope, moody, epic, gorgeous, film grain quality sharp focus beautiful detailed intricate stunning amazing epic".
-
-> [!TIP]
-> You should also use a [*offset noise*](https://www.crosslabs.org//blog/diffusion-with-offset-noise) LoRA to improve the contrast in bright and dark images and create better lighting overall. This [LoRA](https://hf.co/stabilityai/stable-diffusion-xl-base-1.0/blob/main/sd_xl_offset_example-lora_1.0.safetensors) is available from [stabilityai/stable-diffusion-xl-base-1.0](https://hf.co/stabilityai/stable-diffusion-xl-base-1.0).
-
-Start by defining certain styles and a list of words (you can check out a more comprehensive list of [words](https://hf.co/LykosAI/GPT-Prompt-Expansion-Fooocus-v2/blob/main/positive.txt) and [styles](https://github.com/lllyasviel/Fooocus/tree/main/sdxl_styles) used by Fooocus) to enhance a prompt with.
-
-```py
-import torch
-from transformers import GenerationConfig, GPT2LMHeadModel, GPT2Tokenizer, LogitsProcessor, LogitsProcessorList
-from diffusers import StableDiffusionXLPipeline
-
-styles = {
-    "cinematic": "cinematic film still of {prompt}, highly detailed, high budget hollywood movie, cinemascope, moody, epic, gorgeous, film grain",
-    "anime": "anime artwork of {prompt}, anime style, key visual, vibrant, studio anime, highly detailed",
-    "photographic": "cinematic photo of {prompt}, 35mm photograph, film, professional, 4k, highly detailed",
-    "comic": "comic of {prompt}, graphic illustration, comic art, graphic novel art, vibrant, highly detailed",
-    "lineart": "line art drawing {prompt}, professional, sleek, modern, minimalist, graphic, line art, vector graphics",
-    "pixelart": " pixel-art {prompt}, low-res, blocky, pixel art style, 8-bit graphics",
-}
-
-words = [
-    "aesthetic", "astonishing", "beautiful", "breathtaking", "composition", "contrasted", "epic", "moody", "enhanced",
-    "exceptional", "fascinating", "flawless", "glamorous", "glorious", "illumination", "impressive", "improved",
-    "inspirational", "magnificent", "majestic", "hyperrealistic", "smooth", "sharp", "focus", "stunning", "detailed",
-    "intricate", "dramatic", "high", "quality", "perfect", "light", "ultra", "highly", "radiant", "satisfying",
-    "soothing", "sophisticated", "stylish", "sublime", "terrific", "touching", "timeless", "wonderful", "unbelievable",
-    "elegant", "awesome", "amazing", "dynamic", "trendy",
-]
-```
-
-You may have noticed in the `words` list, there are certain words that can be paired together to create something more meaningful. For example, the words "high" and "quality" can be combined to create "high quality". Let's pair these words together and remove the words that can't be paired.
-
-```py
-word_pairs = ["highly detailed", "high quality", "enhanced quality", "perfect composition", "dynamic light"]
-
-def find_and_order_pairs(s, pairs):
-    words = s.split()
-    found_pairs = []
-    for pair in pairs:
-        pair_words = pair.split()
-        if pair_words[0] in words and pair_words[1] in words:
-            found_pairs.append(pair)
-            words.remove(pair_words[0])
-            words.remove(pair_words[1])
-
-    for word in words[:]:
-        for pair in pairs:
-            if word in pair.split():
-                words.remove(word)
-                break
-    ordered_pairs = ", ".join(found_pairs)
-    remaining_s = ", ".join(words)
-    return ordered_pairs, remaining_s
-```
-
-Next, implement a custom [`~transformers.LogitsProcessor`] class that assigns tokens in the `words` list a value of 0 and assigns tokens not in the `words` list a negative value so they aren't picked during generation. This way, generation is biased towards words in the `words` list. After a word from the list is used, it is also assigned a negative value so it isn't picked again.
-
-```py
-class CustomLogitsProcessor(LogitsProcessor):
-    def __init__(self, bias):
-        super().__init__()
-        self.bias = bias
-
-    def __call__(self, input_ids, scores):
-        if len(input_ids.shape) == 2:
-            last_token_id = input_ids[0, -1]
-            self.bias[last_token_id] = -1e10
-        return scores + self.bias
-
-word_ids = [tokenizer.encode(word, add_prefix_space=True)[0] for word in words]
-bias = torch.full((tokenizer.vocab_size,), -float("Inf")).to("cuda")
-bias[word_ids] = 0
-processor = CustomLogitsProcessor(bias)
-processor_list = LogitsProcessorList([processor])
-```
-
-Combine the prompt and the `cinematic` style prompt defined in the `styles` dictionary earlier.
-
-```py
-prompt = "a cat basking in the sun on a roof in Turkey"
-style = "cinematic"
-
-prompt = styles[style].format(prompt=prompt)
-prompt
-"cinematic film still of a cat basking in the sun on a roof in Turkey, highly detailed, high budget hollywood movie, cinemascope, moody, epic, gorgeous, film grain"
-```
-
-Load a GPT2 tokenizer and model from the [Gustavosta/MagicPrompt-Stable-Diffusion](https://huggingface.co/Gustavosta/MagicPrompt-Stable-Diffusion) checkpoint (this specific checkpoint is trained to generate prompts) to enhance the prompt.
-
-```py
-tokenizer = GPT2Tokenizer.from_pretrained("Gustavosta/MagicPrompt-Stable-Diffusion")
-model = GPT2LMHeadModel.from_pretrained("Gustavosta/MagicPrompt-Stable-Diffusion", torch_dtype=torch.float16).to(
-    "cuda"
-)
-model.eval()
-
-inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
-token_count = inputs["input_ids"].shape[1]
-max_new_tokens = 50 - token_count
-
-generation_config = GenerationConfig(
-    penalty_alpha=0.7,
-    top_k=50,
-    eos_token_id=model.config.eos_token_id,
-    pad_token_id=model.config.eos_token_id,
-    pad_token=model.config.pad_token_id,
-    do_sample=True,
-)
-
-with torch.no_grad():
-    generated_ids = model.generate(
-        input_ids=inputs["input_ids"],
-        attention_mask=inputs["attention_mask"],
-        max_new_tokens=max_new_tokens,
-        generation_config=generation_config,
-        logits_processor=proccesor_list,
-    )
-```
-
-Then you can combine the input prompt and the generated prompt. Feel free to take a look at what the generated prompt (`generated_part`) is, the word pairs that were found (`pairs`), and the remaining words (`words`). This is all packed together in the `enhanced_prompt`.
-
-```py
-output_tokens = [tokenizer.decode(generated_id, skip_special_tokens=True) for generated_id in generated_ids]
-input_part, generated_part = output_tokens[0][: len(prompt)], output_tokens[0][len(prompt) :]
-pairs, words = find_and_order_pairs(generated_part, word_pairs)
-formatted_generated_part = pairs + ", " + words
-enhanced_prompt = input_part + ", " + formatted_generated_part
-enhanced_prompt
-["cinematic film still of a cat basking in the sun on a roof in Turkey, highly detailed, high budget hollywood movie, cinemascope, moody, epic, gorgeous, film grain quality sharp focus beautiful detailed intricate stunning amazing epic"]
-```
-
-Finally, load a pipeline and the offset noise LoRA with a *low weight* to generate an image with the enhanced prompt.
-
-```py
-pipeline = StableDiffusionXLPipeline.from_pretrained(
-    "RunDiffusion/Juggernaut-XL-v9", torch_dtype=torch.float16, variant="fp16"
-).to("cuda")
-
-pipeline.load_lora_weights(
-    "stabilityai/stable-diffusion-xl-base-1.0",
-    weight_name="sd_xl_offset_example-lora_1.0.safetensors",
-    adapter_name="offset",
-)
-pipeline.set_adapters(["offset"], adapter_weights=[0.2])
-
-image = pipeline(
-    enhanced_prompt,
-    width=1152,
-    height=896,
-    guidance_scale=7.5,
-    num_inference_steps=25,
-).images[0]
-image
-```
-
-<div class="flex gap-4">
-  <div>
-    <img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/non-enhanced-prompt.png"/>
-    <figcaption class="mt-2 text-center text-sm text-gray-500">"a cat basking in the sun on a roof in Turkey"</figcaption>
-  </div>
-  <div>
-    <img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/enhanced-prompt.png"/>
-    <figcaption class="mt-2 text-center text-sm text-gray-500">"cinematic film still of a cat basking in the sun on a roof in Turkey, highly detailed, high budget hollywood movie, cinemascope, moody, epic, gorgeous, film grain"</figcaption>
-  </div>
-</div>
-
-## Prompt weighting
-
 Prompt weighting provides a way to emphasize or de-emphasize certain parts of a prompt, allowing for more control over the generated image. A prompt can include several concepts, which gets turned into contextualized text embeddings. The embeddings are used by the model to condition its cross-attention layers to generate an image (read the Stable Diffusion [blog post](https://huggingface.co/blog/stable_diffusion) to learn more about how it works).
 
 Prompt weighting works by increasing or decreasing the scale of the text embedding vector that corresponds to its concept in the prompt because you may not necessarily want the model to focus on all concepts equally. The easiest way to prepare the prompt-weighted embeddings is to use [Compel](https://github.com/damian0815/compel), a text prompt-weighting and blending library. Once you have the prompt-weighted embeddings, you can pass them to any pipeline that has a [`prompt_embeds`](https://huggingface.co/docs/diffusers/en/api/pipelines/stable_diffusion/text2img#diffusers.StableDiffusionPipeline.__call__.prompt_embeds) (and optionally [`negative_prompt_embeds`](https://huggingface.co/docs/diffusers/en/api/pipelines/stable_diffusion/text2img#diffusers.StableDiffusionPipeline.__call__.negative_prompt_embeds)) parameter, such as [`StableDiffusionPipeline`], [`StableDiffusionControlNetPipeline`], and [`StableDiffusionXLPipeline`].
@@ -254,7 +55,7 @@ image
   <img class="rounded-xl" src="https://huggingface.co/datasets/hf-internal-testing/diffusers-images/resolve/main/compel/forest_0.png"/>
 </div>
 
-### Weighting
+## Weighting
 
 You'll notice there is no "ball" in the image! Let's use compel to upweight the concept of "ball" in the prompt. Create a [`Compel`](https://github.com/damian0815/compel/blob/main/doc/compel.md#compel-objects) object, and pass it a tokenizer and text encoder:
 
@@ -322,7 +123,7 @@ image
   <img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/compel-pos-neg.png"/>
 </div>
 
-### Blending
+## Blending
 
 You can also create a weighted *blend* of prompts by adding `.blend()` to a list of prompts and passing it some weights. Your blend may not always produce the result you expect because it breaks some assumptions about how the text encoder functions, so just have fun and experiment with it!
 
@@ -338,7 +139,7 @@ image
   <img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/compel-blend.png"/>
 </div>
 
-### Conjunction
+## Conjunction
 
 A conjunction diffuses each prompt independently and concatenates their results by their weighted sum. Add `.and()` to the end of a list of prompts to create a conjunction:
 
@@ -354,7 +155,7 @@ image
   <img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/compel-conj.png"/>
 </div>
 
-### Textual inversion
+## Textual inversion
 
 [Textual inversion](../training/text_inversion) is a technique for learning a specific concept from some images which you can use to generate new images conditioned on that concept.
 
@@ -394,7 +195,7 @@ image
   <img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/compel-text-inversion.png"/>
 </div>
 
-### DreamBooth
+## DreamBooth
 
 [DreamBooth](../training/dreambooth) is a technique for generating contextualized images of a subject given just a few images of the subject to train on. It is similar to textual inversion, but DreamBooth trains the full model whereas textual inversion only fine-tunes the text embeddings. This means you should use [`~DiffusionPipeline.from_pretrained`] to load the DreamBooth model (feel free to browse the [Stable Diffusion Dreambooth Concepts Library](https://huggingface.co/sd-dreambooth-library) for 100+ trained models):
 
@@ -420,7 +221,7 @@ image
   <img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/compel-dreambooth.png"/>
 </div>
 
-### Stable Diffusion XL
+## Stable Diffusion XL
 
 Stable Diffusion XL (SDXL) has two tokenizers and text encoders so it's usage is a bit different. To address this, you should pass both tokenizers and encoders to the `Compel` class:
 

docs/source/en/using-diffusers/write_own_pipeline.md

@@ -273,6 +273,7 @@ Lastly, convert the image to a `PIL.Image` to see your generated image!
 ```py
 >>> image = (image / 2 + 0.5).clamp(0, 1).squeeze()
 >>> image = (image.permute(1, 2, 0) * 255).to(torch.uint8).cpu().numpy()
+>>> images = (image * 255).round().astype("uint8")
 >>> image = Image.fromarray(image)
 >>> image
 ```

docs/source/ko/api/pipelines/stable_diffusion/stable_diffusion_xl.md

@@ -313,12 +313,12 @@ from diffusers import StableDiffusionXLPipeline, StableDiffusionXLImg2ImgPipelin
 import torch
 
 pipe = StableDiffusionXLPipeline.from_single_file(
-    "./sd_xl_base_1.0.safetensors", torch_dtype=torch.float16
+    "./sd_xl_base_1.0.safetensors", torch_dtype=torch.float16, variant="fp16", use_safetensors=True
 )
 pipe.to("cuda")
 
 refiner = StableDiffusionXLImg2ImgPipeline.from_single_file(
-    "./sd_xl_refiner_1.0.safetensors", torch_dtype=torch.float16
+    "./sd_xl_refiner_1.0.safetensors", torch_dtype=torch.float16, use_safetensors=True, variant="fp16"
 )
 refiner.to("cuda")
 ```

docs/source/ko/optimization/fp16.md

@@ -12,7 +12,7 @@ specific language governing permissions and limitations under the License.
 
 # 메모리와 속도
 
-메모리 또는 속도에 대해 🤗 Diffusers *추론*을 최적화하기 위한 몇 가지 기술과 아이디어를 제시합니다.
+메모리 또는 속도에 대해 🤗 Diffusers *추론*을 최적화하기 위한 몇 가지 기술과 아이디어를 제시합니다. 
 일반적으로, memory-efficient attention을 위해 [xFormers](https://github.com/facebookresearch/xformers) 사용을 추천하기 때문에, 추천하는 [설치 방법](xformers)을 보고 설치해 보세요.
 
 다음 설정이 성능과 메모리에 미치는 영향에 대해 설명합니다.
@@ -27,7 +27,7 @@ specific language governing permissions and limitations under the License.
 | memory-efficient attention | 2.63s  | x3.61   |
 
 <em>
-   NVIDIA TITAN RTX에서 50 DDIM 스텝의 "a photo of an astronaut riding a horse on mars" 프롬프트로 512x512 크기의 단일 이미지를 생성하였습니다.
+   NVIDIA TITAN RTX에서 50 DDIM 스텝의 "a photo of an astronaut riding a horse on mars" 프롬프트로 512x512 크기의 단일 이미지를 생성하였습니다. 
 </em>
 
 ## cuDNN auto-tuner 활성화하기
@@ -44,11 +44,11 @@ torch.backends.cudnn.benchmark = True
 
 ### fp32 대신 tf32 사용하기  (Ampere 및 이후 CUDA 장치들에서)
 
-Ampere 및 이후 CUDA 장치에서 행렬곱 및 컨볼루션은 TensorFloat32(TF32) 모드를 사용하여 더 빠르지만 약간 덜 정확할 수 있습니다.
-기본적으로 PyTorch는 컨볼루션에 대해 TF32 모드를 활성화하지만 행렬 곱셈은 활성화하지 않습니다.
-네트워크에 완전한 float32 정밀도가 필요한 경우가 아니면 행렬 곱셈에 대해서도 이 설정을 활성화하는 것이 좋습니다.
-이는 일반적으로 무시할 수 있는 수치의 정확도 손실이 있지만, 계산 속도를 크게 높일 수 있습니다.
-그것에 대해 [여기](https://huggingface.co/docs/transformers/v4.18.0/en/performance#tf32)서 더 읽을 수 있습니다.
+Ampere 및 이후 CUDA 장치에서 행렬곱 및 컨볼루션은 TensorFloat32(TF32) 모드를 사용하여 더 빠르지만 약간 덜 정확할 수 있습니다. 
+기본적으로 PyTorch는 컨볼루션에 대해 TF32 모드를 활성화하지만 행렬 곱셈은 활성화하지 않습니다. 
+네트워크에 완전한 float32 정밀도가 필요한 경우가 아니면 행렬 곱셈에 대해서도 이 설정을 활성화하는 것이 좋습니다. 
+이는 일반적으로 무시할 수 있는 수치의 정확도 손실이 있지만, 계산 속도를 크게 높일 수 있습니다. 
+그것에 대해 [여기](https://huggingface.co/docs/transformers/v4.18.0/en/performance#tf32)서 더 읽을 수 있습니다. 
 추론하기 전에 다음을 추가하기만 하면 됩니다:
 
 ```python
@@ -59,13 +59,13 @@ torch.backends.cuda.matmul.allow_tf32 = True
 
 ## 반정밀도 가중치
 
-더 많은 GPU 메모리를 절약하고 더 빠른 속도를 얻기 위해 모델 가중치를 반정밀도(half precision)로 직접 불러오고 실행할 수 있습니다.
+더 많은 GPU 메모리를 절약하고 더 빠른 속도를 얻기 위해 모델 가중치를 반정밀도(half precision)로 직접 불러오고 실행할 수 있습니다. 
 여기에는 `fp16`이라는 브랜치에 저장된 float16 버전의 가중치를 불러오고, 그 때 `float16` 유형을 사용하도록 PyTorch에 지시하는 작업이 포함됩니다.
 
 ```Python
 pipe = StableDiffusionPipeline.from_pretrained(
     "runwayml/stable-diffusion-v1-5",
-
+    
     torch_dtype=torch.float16,
 )
 pipe = pipe.to("cuda")
@@ -75,7 +75,7 @@ image = pipe(prompt).images[0]
 ```
 
 <Tip warning={true}>
-  어떤 파이프라인에서도 [`torch.autocast`](https://pytorch.org/docs/stable/amp.html#torch.autocast) 를 사용하는 것은 검은색 이미지를 생성할 수 있고, 순수한 float16 정밀도를 사용하는 것보다 항상 느리기 때문에 사용하지 않는 것이 좋습니다.
+  어떤 파이프라인에서도 [`torch.autocast`](https://pytorch.org/docs/stable/amp.html#torch.autocast) 를 사용하는 것은 검은색 이미지를 생성할 수 있고, 순수한 float16 정밀도를 사용하는 것보다 항상 느리기 때문에 사용하지 않는 것이 좋습니다. 
 </Tip>
 
 ## 추가 메모리 절약을 위한 슬라이스 어텐션
@@ -95,7 +95,7 @@ from diffusers import StableDiffusionPipeline
 
 pipe = StableDiffusionPipeline.from_pretrained(
     "runwayml/stable-diffusion-v1-5",
-
+    
     torch_dtype=torch.float16,
 )
 pipe = pipe.to("cuda")
@@ -122,7 +122,7 @@ from diffusers import StableDiffusionPipeline
 
 pipe = StableDiffusionPipeline.from_pretrained(
     "runwayml/stable-diffusion-v1-5",
-
+    
     torch_dtype=torch.float16,
 )
 pipe = pipe.to("cuda")
@@ -148,7 +148,7 @@ from diffusers import StableDiffusionPipeline
 
 pipe = StableDiffusionPipeline.from_pretrained(
     "runwayml/stable-diffusion-v1-5",
-
+    
     torch_dtype=torch.float16,
 )
 
@@ -165,7 +165,7 @@ image = pipe(prompt).images[0]
 또 다른 최적화 방법인 <a href="#model_offloading">모델 오프로딩</a>을 사용하는 것을 고려하십시오. 이는 훨씬 빠르지만 메모리 절약이 크지는 않습니다.
 </Tip>
 
-또한 ttention slicing과 연결해서 최소 메모리(< 2GB)로도 동작할 수 있습니다.
+또한 ttention slicing과 연결해서 최소 메모리(< 2GB)로도 동작할 수 있습니다. 
 
 
 ```Python
@@ -174,7 +174,7 @@ from diffusers import StableDiffusionPipeline
 
 pipe = StableDiffusionPipeline.from_pretrained(
     "runwayml/stable-diffusion-v1-5",
-
+    
     torch_dtype=torch.float16,
 )
 
@@ -204,7 +204,7 @@ import torch
 from diffusers import StableDiffusionPipeline
 
 pipe = StableDiffusionPipeline.from_pretrained(
-    "runwayml/stable-diffusion-v1-5",
+    "runwayml/stable-diffusion-v1-5",  
     torch_dtype=torch.float16,
 )
 
@@ -355,7 +355,7 @@ unet_traced = torch.jit.load("unet_traced.pt")
 class TracedUNet(torch.nn.Module):
     def __init__(self):
         super().__init__()
-        self.in_channels = pipe.unet.config.in_channels
+        self.in_channels = pipe.unet.in_channels
         self.device = pipe.unet.device
 
     def forward(self, latent_model_input, t, encoder_hidden_states):
@@ -387,7 +387,7 @@ with torch.inference_mode():
 | A100-SXM4-40GB    	| 18.6it/s            	| 29.it/s                        	|
 | A100-SXM-80GB    	| 18.7it/s            	| 29.5it/s                        	|
 
-이를 활용하려면 다음을 만족해야 합니다:
+이를 활용하려면 다음을 만족해야 합니다: 
  - PyTorch > 1.12
  - Cuda 사용 가능
  - [xformers 라이브러리를 설치함](xformers)

docs/source/ko/using-diffusers/write_own_pipeline.md

@@ -14,7 +14,7 @@ specific language governing permissions and limitations under the License.
 
 [[open-in-colab]]
 
-🧨 Diffusers는 사용자 친화적이며 유연한 도구 상자로, 사용사례에 맞게 diffusion 시스템을 구축 할 수 있도록 설계되었습니다. 이 도구 상자의 핵심은 모델과 스케줄러입니다. [`DiffusionPipeline`]은 편의를 위해 이러한 구성 요소를 번들로 제공하지만, 파이프라인을 분리하고 모델과 스케줄러를 개별적으로 사용해 새로운 diffusion 시스템을 만들 수도 있습니다.
+🧨 Diffusers는 사용자 친화적이며 유연한 도구 상자로, 사용사례에 맞게 diffusion 시스템을 구축 할 수 있도록 설계되었습니다. 이 도구 상자의 핵심은 모델과 스케줄러입니다. [`DiffusionPipeline`]은 편의를 위해 이러한 구성 요소를 번들로 제공하지만, 파이프라인을 분리하고 모델과 스케줄러를 개별적으로 사용해 새로운 diffusion 시스템을 만들 수도 있습니다. 
 
 이 튜토리얼에서는 기본 파이프라인부터 시작해 Stable Diffusion 파이프라인까지 진행하며 모델과 스케줄러를 사용해 추론을 위한 diffusion 시스템을 조립하는 방법을 배웁니다.
 
@@ -36,7 +36,7 @@ specific language governing permissions and limitations under the License.
 
 정말 쉽습니다. 그런데 파이프라인은 어떻게 이렇게 할 수 있었을까요? 파이프라인을 세분화하여 내부에서 어떤 일이 일어나고 있는지 살펴보겠습니다.
 
-위 예시에서 파이프라인에는 [`UNet2DModel`] 모델과 [`DDPMScheduler`]가 포함되어 있습니다. 파이프라인은 원하는 출력 크기의 랜덤 노이즈를 받아 모델을 여러번 통과시켜 이미지의 노이즈를 제거합니다. 각 timestep에서 모델은 *noise residual*을 예측하고 스케줄러는 이를 사용하여 노이즈가 적은 이미지를 예측합니다. 파이프라인은 지정된 추론 스텝수에 도달할 때까지 이 과정을 반복합니다.
+위 예시에서 파이프라인에는 [`UNet2DModel`] 모델과 [`DDPMScheduler`]가 포함되어 있습니다. 파이프라인은 원하는 출력 크기의 랜덤 노이즈를 받아 모델을 여러번 통과시켜 이미지의 노이즈를 제거합니다. 각 timestep에서 모델은 *noise residual*을 예측하고 스케줄러는 이를 사용하여 노이즈가 적은 이미지를 예측합니다. 파이프라인은 지정된 추론 스텝수에 도달할 때까지 이 과정을 반복합니다. 
 
 모델과 스케줄러를 별도로 사용하여 파이프라인을 다시 생성하기 위해 자체적인 노이즈 제거 프로세스를 작성해 보겠습니다.
 
@@ -210,7 +210,7 @@ Stable Diffusion 은 text-to-image *latent diffusion* 모델입니다. latent di
 
 ```py
 >>> latents = torch.randn(
-...     (batch_size, unet.config.in_channels, height // 8, width // 8),
+...     (batch_size, unet.in_channels, height // 8, width // 8),
 ...     generator=generator,
 ...     device=torch_device,
 ... )

examples/README.md

@@ -42,7 +42,7 @@ Training examples show how to pretrain or fine-tune diffusion models for a varie
 | [**Dreambooth**](./dreambooth) | ✅ | - | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/sd_dreambooth_training.ipynb)
 | [**ControlNet**](./controlnet) | ✅ | ✅ | -
 | [**InstructPix2Pix**](./instruct_pix2pix) | ✅ | ✅ | -
-| [**Reinforcement Learning for Control**](./reinforcement_learning)                    | - | - | coming soon.
+| [**Reinforcement Learning for Control**](https://github.com/huggingface/diffusers/blob/main/examples/reinforcement_learning/run_diffusers_locomotion.py)                    | - | - | coming soon.
 
 ## Community
 

examples/advanced_diffusion_training/README.md

@@ -80,7 +80,8 @@ To do so, just specify `--train_text_encoder_ti` while launching training (for r
 Please keep the following points in mind:
 
 * SDXL has two text encoders. So, we fine-tune both using LoRA.
-* When not fine-tuning the text encoders, we ALWAYS precompute the text embeddings to save memory.
+* When not fine-tuning the text encoders, we ALWAYS precompute the text embeddings to save memoםהקרry.
+
 
 ### 3D icon example
 
@@ -233,81 +234,11 @@ In ComfyUI we will load a LoRA and a textual embedding at the same time.
 
 SDXL's VAE is known to suffer from numerical instability issues. This is why we also expose a CLI argument namely `--pretrained_vae_model_name_or_path` that lets you specify the location of a better VAE (such as [this one](https://huggingface.co/madebyollin/sdxl-vae-fp16-fix)).
 
-### DoRA training 
-The advanced script now supports DoRA training too!
-> Proposed in [DoRA: Weight-Decomposed Low-Rank Adaptation](https://arxiv.org/abs/2402.09353), 
-**DoRA** is very similar to LoRA, except it decomposes the pre-trained weight into two components, **magnitude** and **direction** and employs LoRA for _directional_ updates to efficiently minimize the number of trainable parameters. 
-The authors found that by using DoRA, both the learning capacity and training stability of LoRA are enhanced without any additional overhead during inference. 
-
-> [!NOTE]
-> 💡DoRA training is still _experimental_  
-> and is likely to require different hyperparameter values to perform best compared to a LoRA.
-> Specifically, we've noticed 2 differences to take into account your training: 
-> 1. **LoRA seem to converge faster than DoRA** (so a set of parameters that may lead to overfitting when training a LoRA may be working well for a DoRA)
-> 2. **DoRA quality superior to LoRA especially in lower ranks** the difference in quality of DoRA of rank 8 and LoRA of rank 8 appears to be more significant than when training ranks of 32 or 64 for example.  
-> This is also aligned with some of the quantitative analysis shown in the paper. 
-
-**Usage**
-1. To use DoRA you need to install `peft` from main: 
-```bash
-pip install git+https://github.com/huggingface/peft.git
-```
-2. Enable DoRA training by adding this flag
-```bash
---use_dora
-```
-**Inference** 
-The inference is the same as if you train a regular LoRA 🤗
-
-## Conducting EDM-style training
-
-It's now possible to perform EDM-style training as proposed in [Elucidating the Design Space of Diffusion-Based Generative Models](https://arxiv.org/abs/2206.00364). 
-
-simply set:
-
-```diff
-+  --do_edm_style_training \
-```
-
-Other SDXL-like models that use the EDM formulation, such as [playgroundai/playground-v2.5-1024px-aesthetic](https://huggingface.co/playgroundai/playground-v2.5-1024px-aesthetic), can also be DreamBooth'd with the script. Below is an example command:
-
-```bash
-accelerate launch train_dreambooth_lora_sdxl_advanced.py \
-  --pretrained_model_name_or_path="playgroundai/playground-v2.5-1024px-aesthetic"  \
-  --dataset_name="linoyts/3d_icon" \
-  --instance_prompt="3d icon in the style of TOK" \
-  --validation_prompt="a TOK icon of an astronaut riding a horse, in the style of TOK" \
-  --output_dir="3d-icon-SDXL-LoRA" \
-  --do_edm_style_training \
-  --caption_column="prompt" \
-  --mixed_precision="bf16" \
-  --resolution=1024 \
-  --train_batch_size=3 \
-  --repeats=1 \
-  --report_to="wandb"\
-  --gradient_accumulation_steps=1 \
-  --gradient_checkpointing \
-  --learning_rate=1.0 \
-  --text_encoder_lr=1.0 \
-  --optimizer="prodigy"\
-  --train_text_encoder_ti\
-  --train_text_encoder_ti_frac=0.5\
-  --lr_scheduler="constant" \
-  --lr_warmup_steps=0 \
-  --rank=8 \
-  --max_train_steps=1000 \
-  --checkpointing_steps=2000 \
-  --seed="0" \
-  --push_to_hub
-```
-
-> [!CAUTION]
-> Min-SNR gamma is not supported with the EDM-style training yet. When training with the PlaygroundAI model, it's recommended to not pass any "variant".
 
 ### Tips and Tricks
 Check out [these recommended practices](https://huggingface.co/blog/sdxl_lora_advanced_script#additional-good-practices)
 
 ## Running on Colab Notebook
-Check out [this notebook](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/SDXL_Dreambooth_LoRA_advanced_example.ipynb).
+Check out [this notebook](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/SDXL_DreamBooth_LoRA_advanced_example.ipynb). 
 to train using the advanced features (including pivotal tuning), and [this notebook](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/SDXL_DreamBooth_LoRA_.ipynb) to train on a free colab, using some of the advanced features (excluding pivotal tuning)
 

examples/advanced_diffusion_training/train_dreambooth_lora_sd15_advanced.py

@@ -23,7 +23,6 @@ import os
 import re
 import shutil
 import warnings
-from contextlib import nullcontext
 from pathlib import Path
 from typing import List, Optional
 
@@ -71,14 +70,13 @@ from diffusers.utils.import_utils import is_xformers_available
 
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.28.0.dev0")
+check_min_version("0.27.0.dev0")
 
 logger = get_logger(__name__)
 
 
 def save_model_card(
     repo_id: str,
-    use_dora: bool,
     images=None,
     base_model=str,
     train_text_encoder=False,
@@ -90,7 +88,6 @@ def save_model_card(
     vae_path=None,
 ):
     img_str = "widget:\n"
-    lora = "lora" if not use_dora else "dora"
     for i, image in enumerate(images):
         image.save(os.path.join(repo_folder, f"image_{i}.png"))
         img_str += f"""
@@ -142,10 +139,9 @@ to trigger concept `{key}` → use `{tokens}` in your prompt \n
 tags:
 - stable-diffusion
 - stable-diffusion-diffusers
-- diffusers-training
 - text-to-image
 - diffusers
-- {lora}
+- lora
 - template:sd-lora
 {img_str}
 base_model: {base_model}
@@ -655,15 +651,6 @@ def parse_args(input_args=None):
         default=4,
         help=("The dimension of the LoRA update matrices."),
     )
-    parser.add_argument(
-        "--use_dora",
-        action="store_true",
-        default=False,
-        help=(
-            "Wether to train a DoRA as proposed in- DoRA: Weight-Decomposed Low-Rank Adaptation https://arxiv.org/abs/2402.09353. "
-            "Note: to use DoRA you need to install peft from main, `pip install git+https://github.com/huggingface/peft.git`"
-        ),
-    )
     parser.add_argument(
         "--cache_latents",
         action="store_true",
@@ -1215,7 +1202,7 @@ def main(args):
 
             xformers_version = version.parse(xformers.__version__)
             if xformers_version == version.parse("0.0.16"):
-                logger.warning(
+                logger.warn(
                     "xFormers 0.0.16 cannot be used for training in some GPUs. If you observe problems during training, "
                     "please update xFormers to at least 0.0.17. See https://huggingface.co/docs/diffusers/main/en/optimization/xformers for more details."
                 )
@@ -1232,7 +1219,6 @@ def main(args):
     unet_lora_config = LoraConfig(
         r=args.rank,
         lora_alpha=args.rank,
-        use_dora=args.use_dora,
         init_lora_weights="gaussian",
         target_modules=["to_k", "to_q", "to_v", "to_out.0"],
     )
@@ -1244,7 +1230,6 @@ def main(args):
         text_lora_config = LoraConfig(
             r=args.rank,
             lora_alpha=args.rank,
-            use_dora=args.use_dora,
             init_lora_weights="gaussian",
             target_modules=["q_proj", "k_proj", "v_proj", "out_proj"],
         )
@@ -1366,14 +1351,14 @@ def main(args):
 
     # Optimizer creation
     if not (args.optimizer.lower() == "prodigy" or args.optimizer.lower() == "adamw"):
-        logger.warning(
+        logger.warn(
             f"Unsupported choice of optimizer: {args.optimizer}.Supported optimizers include [adamW, prodigy]."
             "Defaulting to adamW"
         )
         args.optimizer = "adamw"
 
     if args.use_8bit_adam and not args.optimizer.lower() == "adamw":
-        logger.warning(
+        logger.warn(
             f"use_8bit_adam is ignored when optimizer is not set to 'AdamW'. Optimizer was "
             f"set to {args.optimizer.lower()}"
         )
@@ -1407,11 +1392,11 @@ def main(args):
         optimizer_class = prodigyopt.Prodigy
 
         if args.learning_rate <= 0.1:
-            logger.warning(
+            logger.warn(
                 "Learning rate is too low. When using prodigy, it's generally better to set learning rate around 1.0"
             )
         if args.train_text_encoder and args.text_encoder_lr:
-            logger.warning(
+            logger.warn(
                 f"Learning rates were provided both for the unet and the text encoder- e.g. text_encoder_lr:"
                 f" {args.text_encoder_lr} and learning_rate: {args.learning_rate}. "
                 f"When using prodigy only learning_rate is used as the initial learning rate."
@@ -1845,12 +1830,7 @@ def main(args):
                 generator = torch.Generator(device=accelerator.device).manual_seed(args.seed) if args.seed else None
                 pipeline_args = {"prompt": args.validation_prompt}
 
-            if torch.backends.mps.is_available():
-                autocast_ctx = nullcontext()
-            else:
-                autocast_ctx = torch.autocast(accelerator.device.type)
-
-                with autocast_ctx:
+                with torch.cuda.amp.autocast():
                     images = [
                         pipeline(**pipeline_args, generator=generator).images[0]
                         for _ in range(args.num_validation_images)
@@ -1975,7 +1955,6 @@ def main(args):
 
         save_model_card(
             model_id if not args.push_to_hub else repo_id,
-            use_dora=args.use_dora,
             images=images,
             base_model=args.pretrained_model_name_or_path,
             train_text_encoder=args.train_text_encoder,

examples/advanced_diffusion_training/train_dreambooth_lora_sdxl_advanced.py

@@ -17,7 +17,6 @@ import argparse
 import gc
 import hashlib
 import itertools
-import json
 import logging
 import math
 import os
@@ -25,7 +24,6 @@ import random
 import re
 import shutil
 import warnings
-from contextlib import nullcontext
 from pathlib import Path
 from typing import List, Optional
 
@@ -39,7 +37,7 @@ import transformers
 from accelerate import Accelerator
 from accelerate.logging import get_logger
 from accelerate.utils import DistributedDataParallelKwargs, ProjectConfiguration, set_seed
-from huggingface_hub import create_repo, hf_hub_download, upload_folder
+from huggingface_hub import create_repo, upload_folder
 from packaging import version
 from peft import LoraConfig, set_peft_model_state_dict
 from peft.utils import get_peft_model_state_dict
@@ -57,8 +55,6 @@ from diffusers import (
     AutoencoderKL,
     DDPMScheduler,
     DPMSolverMultistepScheduler,
-    EDMEulerScheduler,
-    EulerDiscreteScheduler,
     StableDiffusionXLPipeline,
     UNet2DConditionModel,
 )
@@ -78,28 +74,13 @@ from diffusers.utils.torch_utils import is_compiled_module
 
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.28.0.dev0")
+check_min_version("0.27.0.dev0")
 
 logger = get_logger(__name__)
 
 
-def determine_scheduler_type(pretrained_model_name_or_path, revision):
-    model_index_filename = "model_index.json"
-    if os.path.isdir(pretrained_model_name_or_path):
-        model_index = os.path.join(pretrained_model_name_or_path, model_index_filename)
-    else:
-        model_index = hf_hub_download(
-            repo_id=pretrained_model_name_or_path, filename=model_index_filename, revision=revision
-        )
-
-    with open(model_index, "r") as f:
-        scheduler_type = json.load(f)["scheduler"][1]
-    return scheduler_type
-
-
 def save_model_card(
     repo_id: str,
-    use_dora: bool,
     images=None,
     base_model=str,
     train_text_encoder=False,
@@ -111,7 +92,6 @@ def save_model_card(
     vae_path=None,
 ):
     img_str = "widget:\n"
-    lora = "lora" if not use_dora else "dora"
     for i, image in enumerate(images):
         image.save(os.path.join(repo_folder, f"image_{i}.png"))
         img_str += f"""
@@ -164,10 +144,9 @@ to trigger concept `{key}` → use `{tokens}` in your prompt \n
 tags:
 - stable-diffusion-xl
 - stable-diffusion-xl-diffusers
-- diffusers-training
 - text-to-image
 - diffusers
-- {lora}
+- lora
 - template:sd-lora
 {img_str}
 base_model: {base_model}
@@ -388,11 +367,6 @@ def parse_args(input_args=None):
             " `args.validation_prompt` multiple times: `args.num_validation_images`."
         ),
     )
-    parser.add_argument(
-        "--do_edm_style_training",
-        action="store_true",
-        help="Flag to conduct training using the EDM formulation as introduced in https://arxiv.org/abs/2206.00364.",
-    )
     parser.add_argument(
         "--with_prior_preservation",
         default=False,
@@ -687,15 +661,6 @@ def parse_args(input_args=None):
         default=4,
         help=("The dimension of the LoRA update matrices."),
     )
-    parser.add_argument(
-        "--use_dora",
-        action="store_true",
-        default=False,
-        help=(
-            "Wether to train a DoRA as proposed in- DoRA: Weight-Decomposed Low-Rank Adaptation https://arxiv.org/abs/2402.09353. "
-            "Note: to use DoRA you need to install peft from main, `pip install git+https://github.com/huggingface/peft.git`"
-        ),
-    )
     parser.add_argument(
         "--cache_latents",
         action="store_true",
@@ -1140,8 +1105,6 @@ def main(args):
             "You cannot use both --report_to=wandb and --hub_token due to a security risk of exposing your token."
             " Please use `huggingface-cli login` to authenticate with the Hub."
         )
-    if args.do_edm_style_training and args.snr_gamma is not None:
-        raise ValueError("Min-SNR formulation is not supported when conducting EDM-style training.")
 
     logging_dir = Path(args.output_dir, args.logging_dir)
 
@@ -1259,19 +1222,7 @@ def main(args):
     )
 
     # Load scheduler and models
-    scheduler_type = determine_scheduler_type(args.pretrained_model_name_or_path, args.revision)
-    if "EDM" in scheduler_type:
-        args.do_edm_style_training = True
-        noise_scheduler = EDMEulerScheduler.from_pretrained(args.pretrained_model_name_or_path, subfolder="scheduler")
-        logger.info("Performing EDM-style training!")
-    elif args.do_edm_style_training:
-        noise_scheduler = EulerDiscreteScheduler.from_pretrained(
-            args.pretrained_model_name_or_path, subfolder="scheduler"
-        )
-        logger.info("Performing EDM-style training!")
-    else:
-        noise_scheduler = DDPMScheduler.from_pretrained(args.pretrained_model_name_or_path, subfolder="scheduler")
-
+    noise_scheduler = DDPMScheduler.from_pretrained(args.pretrained_model_name_or_path, subfolder="scheduler")
     text_encoder_one = text_encoder_cls_one.from_pretrained(
         args.pretrained_model_name_or_path, subfolder="text_encoder", revision=args.revision, variant=args.variant
     )
@@ -1289,12 +1240,7 @@ def main(args):
         revision=args.revision,
         variant=args.variant,
     )
-    latents_mean = latents_std = None
-    if hasattr(vae.config, "latents_mean") and vae.config.latents_mean is not None:
-        latents_mean = torch.tensor(vae.config.latents_mean).view(1, 4, 1, 1)
-    if hasattr(vae.config, "latents_std") and vae.config.latents_std is not None:
-        latents_std = torch.tensor(vae.config.latents_std).view(1, 4, 1, 1)
-
+    vae_scaling_factor = vae.config.scaling_factor
     unet = UNet2DConditionModel.from_pretrained(
         args.pretrained_model_name_or_path, subfolder="unet", revision=args.revision, variant=args.variant
     )
@@ -1359,7 +1305,7 @@ def main(args):
 
             xformers_version = version.parse(xformers.__version__)
             if xformers_version == version.parse("0.0.16"):
-                logger.warning(
+                logger.warn(
                     "xFormers 0.0.16 cannot be used for training in some GPUs. If you observe problems during training, "
                     "please update xFormers to at least 0.0.17. See https://huggingface.co/docs/diffusers/main/en/optimization/xformers for more details."
                 )
@@ -1377,7 +1323,6 @@ def main(args):
     unet_lora_config = LoraConfig(
         r=args.rank,
         lora_alpha=args.rank,
-        use_dora=args.use_dora,
         init_lora_weights="gaussian",
         target_modules=["to_k", "to_q", "to_v", "to_out.0"],
     )
@@ -1389,7 +1334,6 @@ def main(args):
         text_lora_config = LoraConfig(
             r=args.rank,
             lora_alpha=args.rank,
-            use_dora=args.use_dora,
             init_lora_weights="gaussian",
             target_modules=["q_proj", "k_proj", "v_proj", "out_proj"],
         )
@@ -1564,14 +1508,14 @@ def main(args):
 
     # Optimizer creation
     if not (args.optimizer.lower() == "prodigy" or args.optimizer.lower() == "adamw"):
-        logger.warning(
+        logger.warn(
             f"Unsupported choice of optimizer: {args.optimizer}.Supported optimizers include [adamW, prodigy]."
             "Defaulting to adamW"
         )
         args.optimizer = "adamw"
 
     if args.use_8bit_adam and not args.optimizer.lower() == "adamw":
-        logger.warning(
+        logger.warn(
             f"use_8bit_adam is ignored when optimizer is not set to 'AdamW'. Optimizer was "
             f"set to {args.optimizer.lower()}"
         )
@@ -1605,11 +1549,11 @@ def main(args):
         optimizer_class = prodigyopt.Prodigy
 
         if args.learning_rate <= 0.1:
-            logger.warning(
+            logger.warn(
                 "Learning rate is too low. When using prodigy, it's generally better to set learning rate around 1.0"
             )
         if args.train_text_encoder and args.text_encoder_lr:
-            logger.warning(
+            logger.warn(
                 f"Learning rates were provided both for the unet and the text encoder- e.g. text_encoder_lr:"
                 f" {args.text_encoder_lr} and learning_rate: {args.learning_rate}. "
                 f"When using prodigy only learning_rate is used as the initial learning rate."
@@ -1832,19 +1776,6 @@ def main(args):
         disable=not accelerator.is_local_main_process,
     )
 
-    def get_sigmas(timesteps, n_dim=4, dtype=torch.float32):
-        # TODO: revisit other sampling algorithms
-        sigmas = noise_scheduler.sigmas.to(device=accelerator.device, dtype=dtype)
-        schedule_timesteps = noise_scheduler.timesteps.to(accelerator.device)
-        timesteps = timesteps.to(accelerator.device)
-
-        step_indices = [(schedule_timesteps == t).nonzero().item() for t in timesteps]
-
-        sigma = sigmas[step_indices].flatten()
-        while len(sigma.shape) < n_dim:
-            sigma = sigma.unsqueeze(-1)
-        return sigma
-
     if args.train_text_encoder:
         num_train_epochs_text_encoder = int(args.train_text_encoder_frac * args.num_train_epochs)
     elif args.train_text_encoder_ti:  # args.train_text_encoder_ti
@@ -1896,15 +1827,9 @@ def main(args):
                     pixel_values = batch["pixel_values"].to(dtype=vae.dtype)
                     model_input = vae.encode(pixel_values).latent_dist.sample()
 
-                if latents_mean is None and latents_std is None:
-                    model_input = model_input * vae.config.scaling_factor
-                    if args.pretrained_vae_model_name_or_path is None:
-                        model_input = model_input.to(weight_dtype)
-                else:
-                    latents_mean = latents_mean.to(device=model_input.device, dtype=model_input.dtype)
-                    latents_std = latents_std.to(device=model_input.device, dtype=model_input.dtype)
-                    model_input = (model_input - latents_mean) * vae.config.scaling_factor / latents_std
-                    model_input = model_input.to(dtype=weight_dtype)
+                model_input = model_input * vae_scaling_factor
+                if args.pretrained_vae_model_name_or_path is None:
+                    model_input = model_input.to(weight_dtype)
 
                 # Sample noise that we'll add to the latents
                 noise = torch.randn_like(model_input)
@@ -1915,32 +1840,15 @@ def main(args):
                     )
 
                 bsz = model_input.shape[0]
-
                 # Sample a random timestep for each image
-                if not args.do_edm_style_training:
-                    timesteps = torch.randint(
-                        0, noise_scheduler.config.num_train_timesteps, (bsz,), device=model_input.device
-                    )
-                    timesteps = timesteps.long()
-                else:
-                    # in EDM formulation, the model is conditioned on the pre-conditioned noise levels
-                    # instead of discrete timesteps, so here we sample indices to get the noise levels
-                    # from `scheduler.timesteps`
-                    indices = torch.randint(0, noise_scheduler.config.num_train_timesteps, (bsz,))
-                    timesteps = noise_scheduler.timesteps[indices].to(device=model_input.device)
+                timesteps = torch.randint(
+                    0, noise_scheduler.config.num_train_timesteps, (bsz,), device=model_input.device
+                )
+                timesteps = timesteps.long()
 
                 # Add noise to the model input according to the noise magnitude at each timestep
                 # (this is the forward diffusion process)
                 noisy_model_input = noise_scheduler.add_noise(model_input, noise, timesteps)
-                # For EDM-style training, we first obtain the sigmas based on the continuous timesteps.
-                # We then precondition the final model inputs based on these sigmas instead of the timesteps.
-                # Follow: Section 5 of https://arxiv.org/abs/2206.00364.
-                if args.do_edm_style_training:
-                    sigmas = get_sigmas(timesteps, len(noisy_model_input.shape), noisy_model_input.dtype)
-                    if "EDM" in scheduler_type:
-                        inp_noisy_latents = noise_scheduler.precondition_inputs(noisy_model_input, sigmas)
-                    else:
-                        inp_noisy_latents = noisy_model_input / ((sigmas**2 + 1) ** 0.5)
 
                 # time ids
                 add_time_ids = torch.cat(
@@ -1966,7 +1874,7 @@ def main(args):
                     }
                     prompt_embeds_input = prompt_embeds.repeat(elems_to_repeat_text_embeds, 1, 1)
                     model_pred = unet(
-                        inp_noisy_latents if args.do_edm_style_training else noisy_model_input,
+                        noisy_model_input,
                         timesteps,
                         prompt_embeds_input,
                         added_cond_kwargs=unet_added_conditions,
@@ -1984,42 +1892,14 @@ def main(args):
                     )
                     prompt_embeds_input = prompt_embeds.repeat(elems_to_repeat_text_embeds, 1, 1)
                     model_pred = unet(
-                        inp_noisy_latents if args.do_edm_style_training else noisy_model_input,
-                        timesteps,
-                        prompt_embeds_input,
-                        added_cond_kwargs=unet_added_conditions,
+                        noisy_model_input, timesteps, prompt_embeds_input, added_cond_kwargs=unet_added_conditions
                     ).sample
 
-                weighting = None
-                if args.do_edm_style_training:
-                    # Similar to the input preconditioning, the model predictions are also preconditioned
-                    # on noised model inputs (before preconditioning) and the sigmas.
-                    # Follow: Section 5 of https://arxiv.org/abs/2206.00364.
-                    if "EDM" in scheduler_type:
-                        model_pred = noise_scheduler.precondition_outputs(noisy_model_input, model_pred, sigmas)
-                    else:
-                        if noise_scheduler.config.prediction_type == "epsilon":
-                            model_pred = model_pred * (-sigmas) + noisy_model_input
-                        elif noise_scheduler.config.prediction_type == "v_prediction":
-                            model_pred = model_pred * (-sigmas / (sigmas**2 + 1) ** 0.5) + (
-                                noisy_model_input / (sigmas**2 + 1)
-                            )
-                    # We are not doing weighting here because it tends result in numerical problems.
-                    # See: https://github.com/huggingface/diffusers/pull/7126#issuecomment-1968523051
-                    # There might be other alternatives for weighting as well:
-                    # https://github.com/huggingface/diffusers/pull/7126#discussion_r1505404686
-                    if "EDM" not in scheduler_type:
-                        weighting = (sigmas**-2.0).float()
-
                 # Get the target for loss depending on the prediction type
                 if noise_scheduler.config.prediction_type == "epsilon":
-                    target = model_input if args.do_edm_style_training else noise
+                    target = noise
                 elif noise_scheduler.config.prediction_type == "v_prediction":
-                    target = (
-                        model_input
-                        if args.do_edm_style_training
-                        else noise_scheduler.get_velocity(model_input, noise, timesteps)
-                    )
+                    target = noise_scheduler.get_velocity(model_input, noise, timesteps)
                 else:
                     raise ValueError(f"Unknown prediction type {noise_scheduler.config.prediction_type}")
 
@@ -2029,28 +1909,10 @@ def main(args):
                     target, target_prior = torch.chunk(target, 2, dim=0)
 
                     # Compute prior loss
-                    if weighting is not None:
-                        prior_loss = torch.mean(
-                            (weighting.float() * (model_pred_prior.float() - target_prior.float()) ** 2).reshape(
-                                target_prior.shape[0], -1
-                            ),
-                            1,
-                        )
-                        prior_loss = prior_loss.mean()
-                    else:
-                        prior_loss = F.mse_loss(model_pred_prior.float(), target_prior.float(), reduction="mean")
+                    prior_loss = F.mse_loss(model_pred_prior.float(), target_prior.float(), reduction="mean")
 
                 if args.snr_gamma is None:
-                    if weighting is not None:
-                        loss = torch.mean(
-                            (weighting.float() * (model_pred.float() - target.float()) ** 2).reshape(
-                                target.shape[0], -1
-                            ),
-                            1,
-                        )
-                        loss = loss.mean()
-                    else:
-                        loss = F.mse_loss(model_pred.float(), target.float(), reduction="mean")
+                    loss = F.mse_loss(model_pred.float(), target.float(), reduction="mean")
                 else:
                     # Compute loss-weights as per Section 3.4 of https://arxiv.org/abs/2303.09556.
                     # Since we predict the noise instead of x_0, the original formulation is slightly changed.
@@ -2173,18 +2035,17 @@ def main(args):
                 # We train on the simplified learning objective. If we were previously predicting a variance, we need the scheduler to ignore it
                 scheduler_args = {}
 
-                if not args.do_edm_style_training:
-                    if "variance_type" in pipeline.scheduler.config:
-                        variance_type = pipeline.scheduler.config.variance_type
+                if "variance_type" in pipeline.scheduler.config:
+                    variance_type = pipeline.scheduler.config.variance_type
 
-                        if variance_type in ["learned", "learned_range"]:
-                            variance_type = "fixed_small"
+                    if variance_type in ["learned", "learned_range"]:
+                        variance_type = "fixed_small"
 
-                        scheduler_args["variance_type"] = variance_type
+                    scheduler_args["variance_type"] = variance_type
 
-                    pipeline.scheduler = DPMSolverMultistepScheduler.from_config(
-                        pipeline.scheduler.config, **scheduler_args
-                    )
+                pipeline.scheduler = DPMSolverMultistepScheduler.from_config(
+                    pipeline.scheduler.config, **scheduler_args
+                )
 
                 pipeline = pipeline.to(accelerator.device)
                 pipeline.set_progress_bar_config(disable=True)
@@ -2192,12 +2053,8 @@ def main(args):
                 # run inference
                 generator = torch.Generator(device=accelerator.device).manual_seed(args.seed) if args.seed else None
                 pipeline_args = {"prompt": args.validation_prompt}
-                if torch.backends.mps.is_available() or "playground" in args.pretrained_model_name_or_path:
-                    autocast_ctx = nullcontext()
-                else:
-                    autocast_ctx = torch.autocast(accelerator.device.type)
 
-                with autocast_ctx:
+                with torch.cuda.amp.autocast():
                     images = [
                         pipeline(**pipeline_args, generator=generator).images[0]
                         for _ in range(args.num_validation_images)
@@ -2273,18 +2130,15 @@ def main(args):
             # We train on the simplified learning objective. If we were previously predicting a variance, we need the scheduler to ignore it
             scheduler_args = {}
 
-            if not args.do_edm_style_training:
-                if "variance_type" in pipeline.scheduler.config:
-                    variance_type = pipeline.scheduler.config.variance_type
+            if "variance_type" in pipeline.scheduler.config:
+                variance_type = pipeline.scheduler.config.variance_type
 
-                    if variance_type in ["learned", "learned_range"]:
-                        variance_type = "fixed_small"
+                if variance_type in ["learned", "learned_range"]:
+                    variance_type = "fixed_small"
 
-                    scheduler_args["variance_type"] = variance_type
+                scheduler_args["variance_type"] = variance_type
 
-                pipeline.scheduler = DPMSolverMultistepScheduler.from_config(
-                    pipeline.scheduler.config, **scheduler_args
-                )
+            pipeline.scheduler = DPMSolverMultistepScheduler.from_config(pipeline.scheduler.config, **scheduler_args)
 
             # load attention processors
             pipeline.load_lora_weights(args.output_dir)
@@ -2338,7 +2192,6 @@ def main(args):
 
         save_model_card(
             model_id if not args.push_to_hub else repo_id,
-            use_dora=args.use_dora,
             images=images,
             base_model=args.pretrained_model_name_or_path,
             train_text_encoder=args.train_text_encoder,

examples/amused/train_amused.py

@@ -430,9 +430,6 @@ def main(args):
         log_with=args.report_to,
         project_config=accelerator_project_config,
     )
-    # Disable AMP for MPS.
-    if torch.backends.mps.is_available():
-        accelerator.native_amp = False
 
     if accelerator.is_main_process:
         os.makedirs(args.output_dir, exist_ok=True)

examples/community/README_community_scripts.md

@@ -1,232 +0,0 @@
-# Community Scripts
-
-**Community scripts** consist of inference examples using Diffusers pipelines that have been added by the community. 
-Please have a look at the following table to get an overview of all community examples. Click on the **Code Example** to get a copy-and-paste code example that you can try out.
-If a community script doesn't work as expected, please open an issue and ping the author on it.
-
-| Example                                                                                                                               | Description                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              | Code Example                                                                              | Colab                                                                                                                                                                                                              |                                                        Author |
-|:--------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|--------------------------------------------------------------:|
-| Using IP-Adapter with negative noise                                                                                                  | Using negative noise with IP-adapter to better control the generation (see the [original post](https://github.com/huggingface/diffusers/discussions/7167) on the forum for more details)                                                                                                                                                                                                                                                    | [IP-Adapter Negative Noise](#ip-adapter-negative-noise)                                   | | [Álvaro Somoza](https://github.com/asomoza)|
-| asymmetric tiling                                                                                                  |configure seamless image tiling independently for the X and Y axes                                                                                                                                                                                                      | [Asymmetric Tiling](#asymmetric-tiling )                                   | | [alexisrolland](https://github.com/alexisrolland)|
-
-
-## Example usages
-
-### IP Adapter Negative Noise
-
-Diffusers pipelines are fully integrated with IP-Adapter, which allows you to prompt the diffusion model with an image. However, it does not support negative image prompts (there is no `negative_ip_adapter_image` argument) the same way it supports negative text prompts. When you pass an `ip_adapter_image,` it will create a zero-filled tensor as a negative image. This script shows you how to create a negative noise from `ip_adapter_image` and use it to significantly improve the generation quality while preserving the composition of images.
-
-[cubiq](https://github.com/cubiq) initially developed this feature in his [repository](https://github.com/cubiq/ComfyUI_IPAdapter_plus). The community script was contributed by [asomoza](https://github.com/Somoza). You can find more details about this experimentation [this discussion](https://github.com/huggingface/diffusers/discussions/7167)
-
-IP-Adapter without negative noise
-|source|result|
-|---|---|
-|![20240229150812](https://github.com/huggingface/diffusers/assets/5442875/901d8bd8-7a59-4fe7-bda1-a0e0d6c7dffd)|![20240229163923_normal](https://github.com/huggingface/diffusers/assets/5442875/3432e25a-ece6-45f4-a3f4-fca354f40b5b)|
-
-IP-Adapter with negative noise
-|source|result|
-|---|---|
-|![20240229150812](https://github.com/huggingface/diffusers/assets/5442875/901d8bd8-7a59-4fe7-bda1-a0e0d6c7dffd)|![20240229163923](https://github.com/huggingface/diffusers/assets/5442875/736fd15a-36ba-40c0-a7d8-6ec1ac26f788)|
-
-```python
-import torch
-
-from diffusers import AutoencoderKL, DPMSolverMultistepScheduler, StableDiffusionXLPipeline
-from diffusers.models import ImageProjection
-from diffusers.utils import load_image
-
-
-def encode_image(
-    image_encoder,
-    feature_extractor,
-    image,
-    device,
-    num_images_per_prompt,
-    output_hidden_states=None,
-    negative_image=None,
-):
-    dtype = next(image_encoder.parameters()).dtype
-
-    if not isinstance(image, torch.Tensor):
-        image = feature_extractor(image, return_tensors="pt").pixel_values
-
-    image = image.to(device=device, dtype=dtype)
-    if output_hidden_states:
-        image_enc_hidden_states = image_encoder(image, output_hidden_states=True).hidden_states[-2]
-        image_enc_hidden_states = image_enc_hidden_states.repeat_interleave(num_images_per_prompt, dim=0)
-
-        if negative_image is None:
-            uncond_image_enc_hidden_states = image_encoder(
-                torch.zeros_like(image), output_hidden_states=True
-            ).hidden_states[-2]
-        else:
-            if not isinstance(negative_image, torch.Tensor):
-                negative_image = feature_extractor(negative_image, return_tensors="pt").pixel_values
-            negative_image = negative_image.to(device=device, dtype=dtype)
-            uncond_image_enc_hidden_states = image_encoder(negative_image, output_hidden_states=True).hidden_states[-2]
-
-        uncond_image_enc_hidden_states = uncond_image_enc_hidden_states.repeat_interleave(num_images_per_prompt, dim=0)
-        return image_enc_hidden_states, uncond_image_enc_hidden_states
-    else:
-        image_embeds = image_encoder(image).image_embeds
-        image_embeds = image_embeds.repeat_interleave(num_images_per_prompt, dim=0)
-        uncond_image_embeds = torch.zeros_like(image_embeds)
-
-        return image_embeds, uncond_image_embeds
-
-
-@torch.no_grad()
-def prepare_ip_adapter_image_embeds(
-    unet,
-    image_encoder,
-    feature_extractor,
-    ip_adapter_image,
-    do_classifier_free_guidance,
-    device,
-    num_images_per_prompt,
-    ip_adapter_negative_image=None,
-):
-    if not isinstance(ip_adapter_image, list):
-        ip_adapter_image = [ip_adapter_image]
-
-    if len(ip_adapter_image) != len(unet.encoder_hid_proj.image_projection_layers):
-        raise ValueError(
-            f"`ip_adapter_image` must have same length as the number of IP Adapters. Got {len(ip_adapter_image)} images and {len(unet.encoder_hid_proj.image_projection_layers)} IP Adapters."
-        )
-
-    image_embeds = []
-    for single_ip_adapter_image, image_proj_layer in zip(
-        ip_adapter_image, unet.encoder_hid_proj.image_projection_layers
-    ):
-        output_hidden_state = not isinstance(image_proj_layer, ImageProjection)
-        single_image_embeds, single_negative_image_embeds = encode_image(
-            image_encoder,
-            feature_extractor,
-            single_ip_adapter_image,
-            device,
-            1,
-            output_hidden_state,
-            negative_image=ip_adapter_negative_image,
-        )
-        single_image_embeds = torch.stack([single_image_embeds] * num_images_per_prompt, dim=0)
-        single_negative_image_embeds = torch.stack([single_negative_image_embeds] * num_images_per_prompt, dim=0)
-
-        if do_classifier_free_guidance:
-            single_image_embeds = torch.cat([single_negative_image_embeds, single_image_embeds])
-            single_image_embeds = single_image_embeds.to(device)
-
-        image_embeds.append(single_image_embeds)
-
-    return image_embeds
-
-
-vae = AutoencoderKL.from_pretrained(
-    "madebyollin/sdxl-vae-fp16-fix",
-    torch_dtype=torch.float16,
-).to("cuda")
-
-pipeline = StableDiffusionXLPipeline.from_pretrained(
-    "RunDiffusion/Juggernaut-XL-v9",
-    torch_dtype=torch.float16,
-    vae=vae,
-    variant="fp16",
-).to("cuda")
-
-pipeline.scheduler = DPMSolverMultistepScheduler.from_config(pipeline.scheduler.config)
-pipeline.scheduler.config.use_karras_sigmas = True
-
-pipeline.load_ip_adapter(
-    "h94/IP-Adapter",
-    subfolder="sdxl_models",
-    weight_name="ip-adapter-plus_sdxl_vit-h.safetensors",
-    image_encoder_folder="models/image_encoder",
-)
-pipeline.set_ip_adapter_scale(0.7)
-
-ip_image = load_image("source.png")
-negative_ip_image = load_image("noise.png")
-
-image_embeds = prepare_ip_adapter_image_embeds(
-    unet=pipeline.unet,
-    image_encoder=pipeline.image_encoder,
-    feature_extractor=pipeline.feature_extractor,
-    ip_adapter_image=[[ip_image]],
-    do_classifier_free_guidance=True,
-    device="cuda",
-    num_images_per_prompt=1,
-    ip_adapter_negative_image=negative_ip_image,
-)
-
-
-prompt = "cinematic photo of a cyborg in the city, 4k, high quality, intricate, highly detailed"
-negative_prompt = "blurry, smooth, plastic"
-
-image = pipeline(
-    prompt=prompt,
-    negative_prompt=negative_prompt,
-    ip_adapter_image_embeds=image_embeds,
-    guidance_scale=6.0,
-    num_inference_steps=25,
-    generator=torch.Generator(device="cpu").manual_seed(1556265306),
-).images[0]
-
-image.save("result.png")
-```
-
-### Asymmetric Tiling
-Stable Diffusion is not trained to generate seamless textures. However, you can use this simple script to add tiling to your generation. This script is contributed by [alexisrolland](https://github.com/alexisrolland). See more details in the [this issue](https://github.com/huggingface/diffusers/issues/556)
-
-
-|Generated|Tiled|
-|---|---|
-|![20240313003235_573631814](https://github.com/huggingface/diffusers/assets/5442875/eca174fb-06a4-464e-a3a7-00dbb024543e)|![wall](https://github.com/huggingface/diffusers/assets/5442875/b4aa774b-2a6a-4316-a8eb-8f30b5f4d024)|
-
-
-```py
-import torch
-from typing import Optional
-from diffusers import StableDiffusionPipeline
-from diffusers.models.lora import LoRACompatibleConv
-
-def seamless_tiling(pipeline, x_axis, y_axis):
-    def asymmetric_conv2d_convforward(self, input: torch.Tensor, weight: torch.Tensor, bias: Optional[torch.Tensor] = None):
-        self.paddingX = (self._reversed_padding_repeated_twice[0], self._reversed_padding_repeated_twice[1], 0, 0)
-        self.paddingY = (0, 0, self._reversed_padding_repeated_twice[2], self._reversed_padding_repeated_twice[3])
-        working = torch.nn.functional.pad(input, self.paddingX, mode=x_mode)
-        working = torch.nn.functional.pad(working, self.paddingY, mode=y_mode)
-        return torch.nn.functional.conv2d(working, weight, bias, self.stride, torch.nn.modules.utils._pair(0), self.dilation, self.groups)
-    x_mode = 'circular' if x_axis else 'constant'
-    y_mode = 'circular' if y_axis else 'constant'
-    targets = [pipeline.vae, pipeline.text_encoder, pipeline.unet]
-    convolution_layers = []
-    for target in targets:
-        for module in target.modules():
-            if isinstance(module, torch.nn.Conv2d):
-                convolution_layers.append(module)
-    for layer in convolution_layers:
-        if isinstance(layer, LoRACompatibleConv) and layer.lora_layer is None:
-            layer.lora_layer = lambda * x: 0
-        layer._conv_forward = asymmetric_conv2d_convforward.__get__(layer, torch.nn.Conv2d)
-    return pipeline
-
-pipeline = StableDiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16, use_safetensors=True)
-pipeline.enable_model_cpu_offload()
-prompt = ["texture of a red brick wall"]
-seed = 123456
-generator = torch.Generator(device='cuda').manual_seed(seed)
-
-pipeline = seamless_tiling(pipeline=pipeline, x_axis=True, y_axis=True)
-image = pipeline(
-    prompt=prompt,
-    width=512,
-    height=512,
-    num_inference_steps=20,
-    guidance_scale=7,
-    num_images_per_prompt=1,
-    generator=generator
-).images[0]
-seamless_tiling(pipeline=pipeline, x_axis=False, y_axis=False)
-
-torch.cuda.empty_cache()
-image.save('image.png')
-```

examples/community/checkpoint_merger.py

@@ -81,8 +81,6 @@ class CheckpointMergerPipeline(DiffusionPipeline):
 
                 force - Whether to ignore mismatch in model_config.json for the current models. Defaults to False.
 
-                variant - which variant of a pretrained model to load, e.g. "fp16" (None)
-
         """
         # Default kwargs from DiffusionPipeline
         cache_dir = kwargs.pop("cache_dir", None)
@@ -91,7 +89,6 @@ class CheckpointMergerPipeline(DiffusionPipeline):
         proxies = kwargs.pop("proxies", None)
         local_files_only = kwargs.pop("local_files_only", False)
         token = kwargs.pop("token", None)
-        variant = kwargs.pop("variant", None)
         revision = kwargs.pop("revision", None)
         torch_dtype = kwargs.pop("torch_dtype", None)
         device_map = kwargs.pop("device_map", None)
@@ -103,7 +100,7 @@ class CheckpointMergerPipeline(DiffusionPipeline):
         print(f"Combining with alpha={alpha}, interpolation mode={interp}")
 
         checkpoint_count = len(pretrained_model_name_or_path_list)
-        # Ignore result from model_index_json comparison of the two checkpoints
+        # Ignore result from model_index_json comparision of the two checkpoints
         force = kwargs.pop("force", False)
 
         # If less than 2 checkpoints, nothing to merge. If more than 3, not supported for now.
@@ -176,10 +173,7 @@ class CheckpointMergerPipeline(DiffusionPipeline):
         # Step 3:-
         # Load the first checkpoint as a diffusion pipeline and modify its module state_dict in place
         final_pipe = DiffusionPipeline.from_pretrained(
-            cached_folders[0],
-            torch_dtype=torch_dtype,
-            device_map=device_map,
-            variant=variant,
+            cached_folders[0], torch_dtype=torch_dtype, device_map=device_map
         )
         final_pipe.to(self.device)
 
@@ -217,7 +211,7 @@ class CheckpointMergerPipeline(DiffusionPipeline):
                         ]
                         checkpoint_path_2 = files[0] if len(files) > 0 else None
                 # For an attr if both checkpoint_path_1 and 2 are None, ignore.
-                # If at least one is present, deal with it according to interp method, of course only if the state_dict keys match.
+                # If atleast one is present, deal with it according to interp method, of course only if the state_dict keys match.
                 if checkpoint_path_1 is None and checkpoint_path_2 is None:
                     print(f"Skipping {attr}: not present in 2nd or 3d model")
                     continue

examples/community/clip_guided_images_mixing_stable_diffusion.py

@@ -12,12 +12,12 @@ from transformers import CLIPFeatureExtractor, CLIPModel, CLIPTextModel, CLIPTok
 from diffusers import (
     AutoencoderKL,
     DDIMScheduler,
+    DiffusionPipeline,
     DPMSolverMultistepScheduler,
     LMSDiscreteScheduler,
     PNDMScheduler,
     UNet2DConditionModel,
 )
-from diffusers.pipelines.pipeline_utils import DiffusionPipeline, StableDiffusionMixin
 from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion import StableDiffusionPipelineOutput
 from diffusers.utils import PIL_INTERPOLATION
 from diffusers.utils.torch_utils import randn_tensor
@@ -77,7 +77,7 @@ def set_requires_grad(model, value):
         param.requires_grad = value
 
 
-class CLIPGuidedImagesMixingStableDiffusion(DiffusionPipeline, StableDiffusionMixin):
+class CLIPGuidedImagesMixingStableDiffusion(DiffusionPipeline):
     def __init__(
         self,
         vae: AutoencoderKL,
@@ -113,6 +113,16 @@ class CLIPGuidedImagesMixingStableDiffusion(DiffusionPipeline, StableDiffusionMi
         set_requires_grad(self.text_encoder, False)
         set_requires_grad(self.clip_model, False)
 
+    def enable_attention_slicing(self, slice_size: Optional[Union[str, int]] = "auto"):
+        if slice_size == "auto":
+            # half the attention head size is usually a good trade-off between
+            # speed and memory
+            slice_size = self.unet.config.attention_head_dim // 2
+        self.unet.set_attention_slice(slice_size)
+
+    def disable_attention_slicing(self):
+        self.enable_attention_slicing(None)
+
     def freeze_vae(self):
         set_requires_grad(self.vae, False)
 

examples/community/clip_guided_stable_diffusion.py

@@ -10,12 +10,12 @@ from transformers import CLIPImageProcessor, CLIPModel, CLIPTextModel, CLIPToken
 from diffusers import (
     AutoencoderKL,
     DDIMScheduler,
+    DiffusionPipeline,
     DPMSolverMultistepScheduler,
     LMSDiscreteScheduler,
     PNDMScheduler,
     UNet2DConditionModel,
 )
-from diffusers.pipelines.pipeline_utils import DiffusionPipeline, StableDiffusionMixin
 from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion import StableDiffusionPipelineOutput
 
 
@@ -51,7 +51,7 @@ def set_requires_grad(model, value):
         param.requires_grad = value
 
 
-class CLIPGuidedStableDiffusion(DiffusionPipeline, StableDiffusionMixin):
+class CLIPGuidedStableDiffusion(DiffusionPipeline):
     """CLIP guided stable diffusion based on the amazing repo by @crowsonkb and @Jack000
     - https://github.com/Jack000/glid-3-xl
     - https://github.dev/crowsonkb/k-diffusion
@@ -89,6 +89,16 @@ class CLIPGuidedStableDiffusion(DiffusionPipeline, StableDiffusionMixin):
         set_requires_grad(self.text_encoder, False)
         set_requires_grad(self.clip_model, False)
 
+    def enable_attention_slicing(self, slice_size: Optional[Union[str, int]] = "auto"):
+        if slice_size == "auto":
+            # half the attention head size is usually a good trade-off between
+            # speed and memory
+            slice_size = self.unet.config.attention_head_dim // 2
+        self.unet.set_attention_slice(slice_size)
+
+    def disable_attention_slicing(self):
+        self.enable_attention_slicing(None)
+
     def freeze_vae(self):
         set_requires_grad(self.vae, False)